unslop
Pass
Audited by Gen Agent Trust Hub on Oct 8, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill demonstrates an attack surface for indirect prompt injection. \n
- Ingestion points: The skill processes text provided via prompts or read from repository files (e.g., launch-notes.md, readme-excerpt.md). \n
- Boundary markers: Absent. The skill does not specify delimiters or explicit instructions for the agent to ignore embedded commands within the target text being cleaned. \n
- Capability inventory: The skill primarily performs text rewriting within the agent context; no specific dangerous subprocess calls, network operations, or privileged file-system writes are defined in the skill instructions. \n
- Sanitization: Absent. There is no escaping or filtering applied to the external content before the agent processes and rewrites it.
Audit Metadata