domain
Pass
Audited by Gen Agent Trust Hub on Apr 30, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it incorporates external, untrusted content into its decision-making and file-writing process.
- Ingestion points: User-provided plan argument in
SKILL.mdand existing project files (e.g.,docs/*.md,CLAUDE.md). - Boundary markers: No explicit markers or warnings are used to distinguish user input from the skill's operational instructions.
- Capability inventory: The skill allows the agent to create and update files within the
docs/directory. - Sanitization: No sanitization, escaping, or validation of the input content is performed before it is used to modify the project documentation.
Audit Metadata