slop-detector
Pass
Audited by Gen Agent Trust Hub on Sep 3, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill is designed for linguistic analysis and does not utilize sensitive system tools, network resources, or external dependencies. Its operations are limited to reading input text and applying predefined heuristic rules.
- [INDIRECT_PROMPT_INJECTION]: The skill processes external text drafts, which serves as an ingestion point for potentially untrusted data. However, the lack of dangerous capabilities mitigates the risk of exploitation.
- Ingestion points: Processes user-provided draft content and references local files in
corpus/drafts/notes/. - Boundary markers: The instructions do not specify delimiters to separate untrusted draft content from the agent's instructions.
- Capability inventory: The skill does not perform network operations, file system modifications, or command execution; it is restricted to text evaluation.
- Sanitization: No explicit sanitization or escaping of the input draft content is performed.
Audit Metadata