antislop-master
Pass
Audited by Gen Agent Trust Hub on Aug 31, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill framework processes external content during the design audit process, which introduces a potential surface for indirect prompt injection.
- Ingestion points: The audit protocol requires the agent to ingest and analyze external project screens, designs, and code files as part of the scan (SKILL.md).
- Boundary markers: The instructions do not define specific delimiters or instructions to treat ingested content as untrusted data to prevent the agent from following embedded instructions.
- Capability inventory: The skill is configured with access to
Read,Write,Edit,Glob, andGreptools (SKILL.md). - Sanitization: No specific input validation or sanitization routines are defined, though the protocol includes a mandatory human-in-the-loop safeguard where the agent is prohibited from applying changes without explicit user approval.
Audit Metadata