find-unknowns

Pass

Audited by Gen Agent Trust Hub on Sep 5, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill is designed to process information from external sources such as file repositories and web search results to generate structured project plans. This creates a potential surface where malicious instructions embedded in those sources could attempt to influence the agent's output.
  • Ingestion points: The skill instructions in SKILL.md direct the agent to 'Inspect whatever is inspectable — files, repository' and 'search the codebase, files, or the web'.
  • Boundary markers: The instructions do not specify the use of delimiters or clear separation between system instructions and data ingested from external files.
  • Capability inventory: The skill utilizes file reading, file writing (e.g., 'implementation-notes.md', 'decision-log.md', and the launch brief), and information gathering to perform its discovery techniques.
  • Sanitization: There are no specific instructions to sanitize or validate the content retrieved from external sources before it is used to generate the final launch brief.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 5, 2026, 05:37 AM
Security Audit — agent-trust-hub — find-unknowns