ap2-cryptographic-signing

Pass

Audited by Gen Agent Trust Hub on Mar 19, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill's primary purpose is to guide the implementation of secure cryptographic signing processes using industry standards such as SD-JWT, ECDSA, and JCS. The technical content is consistent with legitimate development practices.
  • [EXTERNAL_DOWNLOADS]: The skill fetch instructions target documentation from ap2-protocol.org and implementation examples on GitHub. These references are used for information gathering and do not involve the execution of untrusted remote code.
  • [PROMPT_INJECTION]: An indirect prompt injection surface exists because the skill ingests data from external websites and possesses file-writing and bash capabilities. \n- Ingestion points: WebFetch and WebSearch commands in SKILL.md. \n- Boundary markers: None present. \n- Capability inventory: Bash, Write, and Edit tools are enabled in the skill metadata. \n- Sanitization: The instructions do not specify validation or sanitization of the external content prior to processing.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 19, 2026, 07:32 AM
Security Audit — agent-trust-hub — ap2-cryptographic-signing