dev-docs
Pass
Audited by Gen Agent Trust Hub on Apr 17, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill exhibits an indirect prompt injection surface because it reads untrusted data from project files to populate documentation templates.
- Ingestion points: Project files, architectural decisions, and dependency information read from the local environment (SKILL.md).
- Boundary markers: Absent; there are no instructions to use delimiters or ignore commands embedded within the processed project data.
- Capability inventory: The skill is authorized to use Bash, Read, Write, Glob, Grep, and TodoWrite tools (SKILL.md).
- Sanitization: Absent; content retrieved from the filesystem is interpolated into generated markdown files without validation or escaping.
Audit Metadata