ps-automate-me
Pass
Audited by Gen Agent Trust Hub on Sep 17, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data from agent transcripts to identify user working patterns.\n
- Ingestion points: Reads files from the
agent-transcripts/directory within the workspace (SKILL.md, Step 1).\n - Boundary markers: Not explicitly defined for transcript contents; the skill relies on subagents to produce structured summaries of patterns.\n
- Capability inventory: The skill can write files via the
create-skilltool and execute shell commands viagit(log, commit, branch, pr).\n - Sanitization: No explicit sanitization of transcript content is mentioned; the skill relies on a human-in-the-loop review process (Step 5) before finalizing changes.\n- [COMMAND_EXECUTION]: The skill uses shell commands to interact with the local repository and git history.\n
- Uses
git logto determine the last edit time of existing skills.\n - Uses
gitto create branches, commits, and pull requests for final delivery.
Audit Metadata