compdf-encryt-pdf-decrypt-pdf
Pass
Audited by Gen Agent Trust Hub on Aug 15, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill processes untrusted user PDF documents while having access to network API endpoints and local file storage, which creates an indirect prompt injection surface.
- Ingestion points: User-provided PDF files (SKILL.md).
- Boundary markers: Not specified; instructions do not include markers to separate document content from agent instructions.
- Capability inventory: The skill prepares network API requests and manages a local api_key file (SKILL.md).
- Sanitization: No sanitization or validation of the source document content is mentioned.
Audit Metadata