archive
Pass
Audited by Gen Agent Trust Hub on Mar 30, 2026
Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
- [COMMAND_EXECUTION]: The skill utilizes standard system utilities including
ls,grep, andheadto locate files, andgitcommands (mv,add,commit) to manage versioning and archiving of plan documents in theai-workspace/plans/directory. - [INDIRECT_PROMPT_INJECTION]: The skill ingests data from external sources (git history and branch context) which may contain content from other users or external sources, creating a potential surface for indirect prompt injection.
- Ingestion points: Reads from
git logand branch metadata inSKILL.md(Step 3). - Boundary markers: Absent; there are no instructions to the agent to ignore instructions embedded within the git log.
- Capability inventory: Shell command execution (via
ls,grep,git) and file system write access to modify plan files. - Sanitization: No sanitization or validation of the content retrieved from git logs is performed before processing.
Audit Metadata