skill-goal-extractor

Pass

Audited by Gen Agent Trust Hub on Sep 3, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill's primary function is to ingest and process the complete content of other skills, including all referenced files. This creates a surface where a malicious skill could include hidden instructions designed to manipulate the extractor's output or the agent's behavior.
  • Ingestion points: The skill reads all files and referenced resources within a target skill directory as defined in step 2 of the procedure.
  • Boundary markers: The instructions do not define delimiters or protective markers to separate the analysis instructions from the content being processed.
  • Capability inventory: The skill is authorized to read filesystem content and write a specific markdown file (SKILL-GOALS.md) to the target directory.
  • Sanitization: No sanitization or filtering is performed on the data read from the target directory before it is summarized and presented to the user.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 3, 2026, 12:28 AM
Security Audit — agent-trust-hub — skill-goal-extractor