perf-baseline-manager

Pass

Audited by Gen Agent Trust Hub on Oct 9, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill processes performance metrics and version strings supplied by the user or external systems to generate and store baseline files.
  • Ingestion points: Performance results and version identifiers are ingested from the operational context to consolidate results (referenced in SKILL.md).
  • Boundary markers: Absent. The instructions do not define specific delimiters or warnings to ignore instructions embedded within the performance data or metadata.
  • Capability inventory: The skill requires file-writing capabilities to store JSON files in the {state-dir}/perf/baselines/ directory (referenced in SKILL.md).
  • Sanitization: Absent. There are no instructions to validate or sanitize the <version> parameter, creating a potential path traversal surface if the agent does not restrict file path construction.
Audit Metadata
Risk Level
SAFE
Analyzed
Oct 9, 2026, 09:05 PM