pm-skill-creator
Pass
Audited by Gen Agent Trust Hub on Sep 14, 2026
Risk Level: SAFE
Full Analysis
- [COMMAND_EXECUTION]: The skill references local utility scripts (e.g.,
scripts/check-skill-metadata.py,scripts/test-a-skill.sh,scripts/find-a-skill.sh) used for validation and development workflows. These represent standard vendor-provided tooling within the repository environment. - [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest user-provided raw content to generate markdown drafts. It incorporates instructions for the agent to analyze, infer, and confirm interpretations before generating output, which acts as a safeguard during the authoring process.
- [SAFE]: No evidence of malicious prompt injection, data exfiltration, obfuscation, or unauthorized privilege escalation was detected. The skill's behavior is consistent with its stated purpose as a conversational authoring assistant.
Audit Metadata