agent-skills-architect
Pass
Audited by Gen Agent Trust Hub on Apr 13, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: No malicious patterns or security risks were identified. The skill's operations, such as fetching documentation from 'agentskills.io' and referencing 'vercel-labs' repositories, are appropriate for its function as a skill development and auditing tool.\n- [PROMPT_INJECTION]: The skill possesses a natural attack surface for indirect prompt injection because its core function involves processing and auditing external files provided by users.\n
- Ingestion points: Audited skill files (e.g., 'SKILL.md', scripts) and 'skills.sh' URLs.\n
- Boundary markers: The instructions do not use delimiters or explicit warnings to ignore instructions embedded in the audited data.\n
- Capability inventory: The skill can read local files, access the network for documentation, and generate ZIP artifacts.\n
- Sanitization: There is no mention of sanitizing or escaping content from the files being audited.
Audit Metadata