deslop
Pass
Audited by Gen Agent Trust Hub on Sep 24, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted input from files and URLs, which could potentially contain malicious prompts intended to manipulate the agent.
- Ingestion points: External data enters the skill context through inline text inputs, file reads, and URL fetching as described in the 'Input Handling' section of
SKILL.md. - Boundary markers: There are no explicit delimiters or specific instructions for the agent to ignore commands that might be embedded within the provided prose.
- Capability inventory: The skill performs file system reads and utilizes browsing capabilities to retrieve remote content for verification and review.
- Sanitization: The instructions do not specify any validation or sanitization routines for the external text before it is processed for rewriting.
Audit Metadata