gendoc
Pass
Audited by Gen Agent Trust Hub on Jun 21, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it ingests and processes untrusted data from project files and remote URLs to fulfill its documentation tasks.
- Ingestion points: Analysis of manifests, project trees, existing docs, LICENSE, CI, and remote URLs (SKILL.md).
- Boundary markers: Absent. No specific delimiters are defined in the instructions to isolate external project content.
- Capability inventory: Authorized to perform file-write operations for documentation (README.md, README.ko.md, ARCHITECTURE.md, USAGE.md).
- Sanitization: Absent. The skill does not describe processes for sanitizing content extracted from analyzed project files.
Audit Metadata