st-create-plan
Pass
Audited by Gen Agent Trust Hub on Jun 14, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill instructs the agent to follow instructions contained in external hook files, creating a surface for indirect prompt injection.
- Ingestion points: Content is read from
<root>/config/hooks/PRE_PLAN.mdand<root>/config/hooks/POST_PLAN.mdas described inSKILL.md. - Boundary markers: Absent. The skill explicitly directs the agent to "execute the instructions it contains" without providing context delimiters or warnings to ignore embedded commands.
- Capability inventory: The agent has the ability to traverse the file system (via
scripts/find-strikethroo-root.cjs), read project configuration, and write new markdown files to the repository. - Sanitization: Absent. There is no validation or filtering of the content within the hook files before the agent is prompted to follow its instructions.
Audit Metadata