Agency
Pass
Audited by Gen Agent Trust Hub on Jun 6, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [SAFE]: The skill consists entirely of organizational markdown documentation and templates for agency management. No executable scripts, binary files, or suspicious command-line operations were detected.
- [PROMPT_INJECTION]: The workflow involves processing external data (client intake and feedback), which creates a surface for indirect prompt injection. This is classified as low risk due to the absence of exploitable capabilities.
- Ingestion points: Intake process in 'onboarding.md' and feedback parsing in 'communication.md'.
- Boundary markers: No explicit delimiters or instructions to ignore embedded commands are present in the templates.
- Capability inventory: The skill is restricted to local file operations within '~/agency/'. It has no access to subprocesses, network requests, or sensitive system directories.
- Sanitization: There are no documented steps for sanitizing or validating the content of ingested client communications.
Audit Metadata