wk-retro
Pass
Audited by Gen Agent Trust Hub on Aug 24, 2026
Risk Level: SAFEPROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [PROMPT_INJECTION]: The skill processes untrusted data from git logs and session history to generate summaries, presenting a risk of indirect prompt injection.
- Ingestion points: Git history and chat transcripts are read in SKILL.md to gather session context.
- Boundary markers: No explicit delimiters or instructions are used to isolate untrusted data from the agent instructions.
- Capability inventory: The skill uses Bash for git operations and Write/Edit to update agent memory and log files.
- Sanitization: A validation gate in SKILL.md uses grep and printenv to scrub environment variables and local file paths before writing output to the retrospective logs.
- [COMMAND_EXECUTION]: Shell commands are used to retrieve repository state and perform data validation. This includes running git log, git diff, and grep-based checks on generated content within the Bash tool's permitted scope.
Audit Metadata