agent-capability-discovery

Pass

Audited by Gen Agent Trust Hub on Oct 22, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill's primary function is to ingest metadata from arbitrary skill.yaml files, which serves as a vector for indirect prompt injection.
  • Ingestion points: Files are read from the base_directory input, specifically targeted at skill.yaml definitions across the local repository.
  • Boundary markers: The output format (markdown, JSON, or YAML) does not implement explicit delimiters or "ignore embedded instructions" warnings to prevent the agent from treating discovered metadata as authoritative commands.
  • Capability inventory: The skill performs recursive directory traversal and file reading to extract descriptive text.
  • Sanitization: There is no evidence of sanitization for the 'capabilities' or 'description' fields extracted from external files before they are presented to the master agent for decision-making.
Audit Metadata
Risk Level
SAFE
Analyzed
Oct 22, 2026, 03:51 PM