perf-theory-gatherer

Pass

Audited by Gen Agent Trust Hub on Oct 9, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data from the repository (git history, grep results) to generate hypotheses.
  • Ingestion points: Git history, repository map, and grep results (SKILL.md).
  • Boundary markers: Absent; the skill does not specify delimiters or instructions to ignore embedded instructions within the code or git history.
  • Capability inventory: Read-only access to repository data using git and grep tools (SKILL.md). No file write or network communication capabilities are utilized.
  • Sanitization: Absent; no sanitization of the content extracted from the repository is described.
Audit Metadata
Risk Level
SAFE
Analyzed
Oct 9, 2026, 09:02 PM