framer-prod-checklist
Pass
Audited by Gen Agent Trust Hub on Sep 9, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill instructions require the agent to process external data, specifically "evidence" and "owner decisions," to validate checklist controls, which creates a potential surface for indirect prompt injection.
- Ingestion points: The instructions in
SKILL.mddirect the agent to "Attach evidence or an owner decision to every control," implying the processing of untrusted external content. - Boundary markers: There are no boundary markers, delimiters, or explicit instructions to ignore embedded commands within the ingested evidence.
- Capability inventory: The skill environment provides access to
Read,Grep, andBash(curl:*)tools, which could be targeted if malicious instructions are present in the ingested data. - Sanitization: No sanitization, validation, or filtering procedures for the external evidence are defined in the skill.
Audit Metadata