The Agent Skills Directory

[SAFE]: No malicious behavior, prompt injection, or data exfiltration patterns were detected in the skill instructions or metadata.
[INDIRECT_PROMPT_INJECTION]: The skill possesses an attack surface for indirect prompt injection as it processes external project documentation to generate outputs.
Ingestion points: Reads docs/product/project-plan.md and docs/product/.ompm/metrics.json (SKILL.md).
Boundary markers: Absent; the skill does not wrap the ingested documentation content in delimiters.
Capability inventory: Limited to writing markdown files at docs/product/release-plan.md and docs/product/release-notes/[version].md (SKILL.md).
Sanitization: Absent; the skill performs direct interpolation of source data into output templates.

release-management