pstack-automate-me
Pass
Audited by Gen Agent Trust Hub on Oct 15, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted repository history and recent session logs as discovery inputs to generate automation patterns. Ingestion points: Repository-scoped history and recent session history (SKILL.md, step 2). Boundary markers: Not explicitly defined in the instructions. Capability inventory: The skill performs file system modifications via source edits and draft pull requests (SKILL.md, step 5). Sanitization: The workflow mandates human review and explicit approval of all proposed changes before application (SKILL.md, step 5).
- [EXTERNAL_DOWNLOADS]: The skill references source code and maintenance guidelines from a repository on GitHub. Evidence: Canonical source at github.com/cursor/plugins (UPSTREAM.md). This reference identifies a well-known service provider and is used for upstream tracking and local adaptations.
Audit Metadata