ship-debrief
Pass
Audited by Gen Agent Trust Hub on Sep 18, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted data from git commit history and user responses to synthesize debriefs and update local project files.
- Ingestion points: Git history data and user answers are read into the agent context in SKILL.md.
- Boundary markers: The instructions do not define delimiters or specific warnings to ignore instructions that might be embedded within commit messages or diffs.
- Capability inventory: The skill has access to the Bash tool for repository inspection and the Write tool for updating the
.claude/ship.local.mdfile. - Sanitization: No validation or sanitization of the ingested git metadata or user input is performed before the synthesis and file writing steps.
- [COMMAND_EXECUTION]: The skill utilizes the Bash tool to execute git log commands for reviewing the last seven days of activity.
Audit Metadata