game-postmortem
Pass
Audited by Gen Agent Trust Hub on Apr 12, 2026
Risk Level: SAFE
Full Analysis
- [COMMAND_EXECUTION]: The skill utilizes dynamic context injection to execute benign shell commands such as
git log,git shortlog, andgh issue listto automatically populate project statistics. These operations are scoped to the project's local directory and authenticated GitHub context, serving the skill's stated purpose for post-mortem analysis. - [PROMPT_INJECTION]: The skill processes data from external sources including git history, GitHub issues, and local retrospective notes, which establishes an indirect prompt injection surface.
- Ingestion points: Git commit history, GitHub issue data, and retrospective files in
production/sprints/. - Boundary markers: Not explicitly defined for the ingested data.
- Capability inventory: Includes shell command execution (
Bash), file creation (Write), and document modification (Edit). - Sanitization: No explicit sanitization of ingested content is performed, though the workflow focuses on structured pattern analysis.
Audit Metadata