pm-toolkit

Pass

Audited by Gen Agent Trust Hub on May 14, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: No malicious patterns, hardcoded credentials, or unauthorized network operations were detected in the skill's instructions or configuration.\n- [INDIRECT_PROMPT_INJECTION]: The skill processes external, untrusted data (meeting minutes) to extract specification changes. While the primary capability is writing Markdown files, malicious instructions embedded in the processed minutes could potentially influence the generated output.\n
  • Ingestion points: Meeting minutes analyzed via the extraction prompt in SKILL.md (and translated versions).\n
  • Boundary markers: Absent; there are no specific delimiters or instructions to ignore embedded commands within the input data.\n
  • Capability inventory: File-write operations to the output/pm/ directory as specified in the Output Format section.\n
  • Sanitization: Absent; the skill does not perform validation or escaping of the meeting minute content before processing.
Audit Metadata
Risk Level
SAFE
Analyzed
May 14, 2026, 05:58 AM
Security Audit — agent-trust-hub — pm-toolkit