agents-md-generator
Pass
Audited by Gen Agent Trust Hub on Feb 17, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [Indirect Prompt Injection] (LOW): The skill's primary function is to analyze external repository data (tech stack, directory structures, code patterns) to generate documentation, which creates a surface for indirect prompt injection.
- Ingestion points: Phase 1 (Repository Analysis) involves reading and reporting on codebase contents.
- Boundary markers: Absent; the skill does not specify the use of delimiters or 'ignore' instructions for the data it processes from the repository.
- Capability inventory: The skill itself is restricted to generating text templates and does not invoke dangerous capabilities like network access, persistent storage, or arbitrary command execution.
- Sanitization: Absent; the instructions do not include mechanisms to sanitize or escape data ingested from the analyzed files.
Audit Metadata