Requirements
- Target platform
- OpenClaw
- Install method
- Manual import
- Extraction
- Extract archive
- Prerequisites
- OpenClaw
- Primary doc
- SKILL.md
Tencent SkillHub Β· AI
agent-card-signing-auditor
Helps audit Agent Card signing practices in A2A protocol implementations. Identifies missing signatures, weak signing schemes, and revocation gaps that allow...
skill openclawclawhub Free
Helps audit Agent Card signing practices in A2A protocol implementations. Identifies missing signatures, weak signing schemes, and revocation gaps that allow...
β¬ 0 downloads β
0 stars Unverified but indexed
Install for OpenClaw
Quick setup
- Download the package from Yavira.
- Extract the archive and review SKILL.md first.
- Import or place the package into your OpenClaw setup.
Package facts
- Download mode
- Yavira redirect
- Package format
- ZIP package
- Source platform
- Tencent SkillHub
- What's included
- SKILL.md
Validation
- Use the Yavira download entry.
- Review SKILL.md after the package is downloaded.
- Confirm the extracted package contains the expected setup assets.
Install with your agent
Agent handoff
Hand the extracted package to your coding agent with a concrete install brief instead of figuring it out manually.
- Download the package from Yavira.
- Extract it into a folder your agent can access.
- Paste one of the prompts below and point your agent at the extracted folder.
New install
I downloaded a skill package from Yavira. Read SKILL.md from the extracted folder and install it by following the included instructions. Tell me what you changed and call out any manual steps you could not complete.
Upgrade existing
I downloaded an updated skill package from Yavira. Read SKILL.md from the extracted folder, compare it with my current installation, and upgrade it while preserving any custom configuration unless the package docs explicitly say otherwise. Summarize what changed and any follow-up checks I should run.
Trust & source
Release facts
- Source
- Tencent SkillHub
- Verification
- Indexed source record
- Version
- 1.0.0
Provenance
- Publisher
- andyxinweiminicloud
- Source page
- View original listing
- Canonical URL
- Open canonical page
Documentation
A2A Says Signing Is Optional. That's the Problem.
Helps identify gaps in Agent Card signing that allow impersonation, identity spoofing, and unverifiable capability claims in agent-to-agent trust handshakes.
Problem
The A2A Protocol specifies Agent Cards as the primary mechanism for agent identity and capability advertisement. An Agent Card tells other agents: who you are, what you can do, and what trust level you claim. But the A2A spec makes signing optional β "recommended but not required." In an ecosystem where 15-18% of published skills are already confirmed malicious, optional signing means any agent can present any identity and any capability claim with zero verifiable proof. The trust handshake that underpins all A2A interactions is built on a foundation that most implementations don't verify.
What This Checks
This auditor examines Agent Card signing practices across five dimensions: Signature presence β Does the Agent Card include a signature field? Many implementations omit it entirely, relying on the marketplace's account verification as a trust proxy. That's a single point of failure β marketplace accounts can be compromised or impersonated Signing scheme strength β If a signature is present, which algorithm was used? RSA-1024 and ECDSA with weak curves are no longer adequate for high-stakes agent interactions. Checks against current recommendations (Ed25519, RSA-2048+ with PSS padding) Key transparency β Is the signing key published in a verifiable key transparency log or JWKS endpoint? A signature is only as trustworthy as the process by which you obtained the public key to verify it Revocation mechanism β Does the signing infrastructure include a revocation path? Signing keys get compromised. An Agent Card signed with a compromised key looks identical to a legitimately-signed one without revocation checking Rotation audit trail β Has the signing key changed? When? With what announcement? Key rotation events that coincide with capability changes or that happen without public announcement are higher-risk than routine scheduled rotations
How to Use
Input: Provide one of: An Agent Card JSON object to audit directly An agent endpoint URL to fetch and audit the Agent Card A set of Agent Card snapshots to compare for rotation events Output: A signing audit report containing: Signature presence and scheme assessment Key transparency verification result Revocation mechanism check Rotation history (if available) Risk rating: STRONG / ADEQUATE / WEAK / UNSIGNED Specific recommendations for remediation
Example
Input: Audit Agent Card for data-processing-agent.example πͺͺ AGENT CARD SIGNING AUDIT Agent: data-processing-agent.example Card version: 2.1.0 Audit timestamp: 2025-03-15T10:30:00Z Signature presence: β οΈ ABSENT Agent Card contains no signature field Identity claim is unverifiable β relies entirely on marketplace account trust Risk: any agent can claim this identity or capabilities without detection Signing scheme: N/A (unsigned) Key transparency: β NOT CONFIGURED No JWKS endpoint referenced in Agent Card No key transparency log entry found Revocation mechanism: β NONE No revocation endpoint specified No CRL or OCSP equivalent configured Rotation history: N/A Risk rating: UNSIGNED This Agent Card makes identity and capability claims that cannot be cryptographically verified. In a trust-sensitive interaction, treat all capability claims as unverified assertions. Recommended actions: 1. Implement Ed25519 signing for Agent Card with JWKS endpoint 2. Register signing key in a public key transparency log 3. Add revocation endpoint to Agent Card metadata 4. Establish rotation policy with public announcement process
Related Tools
publisher-identity-verifier β Audits publisher identity at the marketplace level; signing auditor checks the A2A protocol layer trust-decay-monitor β Tracks trust freshness over time; signing provides the baseline trust claim that decays protocol-doc-auditor β Checks documentation trust signals; Agent Card signing is the machine-readable equivalent attestation-chain-auditor β Validates the full trust chain from signing key to capability claim
Limitations
This auditor evaluates signing practices based on publicly observable Agent Card metadata. It cannot assess the security of key storage practices on the agent's host system, verify that the private key holder is actually the claimed agent, or detect signing key compromise that has not yet been publicly disclosed. A well-formed signed Agent Card with strong cryptography can still represent a compromised or malicious agent β signing establishes identity, not trustworthiness. Use in combination with behavioral analysis tools for comprehensive trust assessment.
Category context
Agent frameworks, memory systems, reasoning layers, and model-native orchestration.
Source: Tencent SkillHub
Largest current source with strong distribution and engagement signals.
Package contents
Included in package
1 Docs
- SKILL.md