release-manager
Pass
Audited by Gen Agent Trust Hub on Oct 28, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: No security issues were identified in the analysis of the scripts and documentation. The skill facilitates release management workflows by parsing conventional commits and structured release plans without executing arbitrary code or performing unauthorized network operations.
- [INDIRECT_PROMPT_INJECTION]: The skill provides an attack surface for indirect prompt injection by processing external, untrusted data such as git commit messages and JSON release plans. This data is then formatted into reports that the agent processes. This is documented as a risk factor inherent to the skill's purpose.
- Ingestion points: Git log data provided via stdin to
changelog_generator.pyandversion_bumper.py, and JSON release plan files processed byrelease_planner.py. - Boundary markers: No explicit delimiters or warnings are added to the generated markdown or text outputs to warn the agent about potentially malicious instructions embedded in the source data.
- Capability inventory: The skill empowers the agent to analyze repository history, generate structured release artifacts, and recommend release-related shell commands.
- Sanitization: The scripts utilize regular expressions to extract structured data from commit headers and footers, which provides a layer of structural validation, though it does not sanitize natural language descriptions.
Audit Metadata