stay-positive
Pass
Audited by Gen Agent Trust Hub on Oct 17, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process untrusted human-facing prose (e.g., feedback, correspondence, articles) which creates a surface for indirect prompt injection if the input content contains malicious instructions.
- Ingestion points: Untrusted prose is ingested during the 'Audit', 'Edit', and 'Draft' workflows defined in
SKILL.mdand referenced inREADME.md. - Boundary markers: The instructions do not specify the use of delimiters or clear boundary markers to isolate untrusted input from the agent's core instructions.
- Capability inventory: The skill possesses the capability to modify files ('edit the requested file' in the 'Edit' mode section of
SKILL.md) and return modified text to the user. - Sanitization: There are no explicit instructions for sanitizing, escaping, or validating the input prose before the agent processes or interpolates it into the workflow.
Audit Metadata