unslop
Pass
Audited by Gen Agent Trust Hub on Sep 21, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process untrusted text provided by the user, which presents a surface for potential indirect prompt injection attacks.
- Ingestion points: The
SKILL.mdfile specifies that the agent should scan user-provided text such as READMEs, posts, emails, and landing pages. - Boundary markers: The skill includes instructions to return the cleaned text as a separate artifact and to keep findings outside of it, which serves as a mitigation against output-based confusion.
- Capability inventory: The skill does not explicitly request tool permissions, but it operates in an environment where agents typically have access to file systems and terminal commands.
- Sanitization: No sanitization or filtering of the input text is prescribed; the skill explicitly instructs the agent to preserve code blocks, commands, and URLs exactly as found.
Audit Metadata