simplify-audit
Pass
Audited by Gen Agent Trust Hub on Aug 31, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill instructs the agent to ingest and analyze a broad range of repository artifacts, which creates a surface for indirect prompt injection if those files contain malicious instructions meant to influence the agent.
- Ingestion points: The agent is directed to read repository instructions, architectural authority documents, configuration files, deployment manifests, public APIs, and general documentation (SKILL.md).
- Capability inventory: The skill assumes the agent has extensive read access to the target repository's filesystem.
- Boundary markers: The skill lacks explicit instructions or markers to distinguish between the audit instructions and the content being audited, increasing the risk of the agent following instructions found within the audited data.
- Sanitization: There are no provisions for sanitizing or validating the content read from the repository before it is processed by the agent.
Audit Metadata