unslop
Pass
Audited by Gen Agent Trust Hub on Sep 22, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill provides instructional guidelines for text manipulation and writing style. It does not contain executable code, scripts, or remote references.
- [INDIRECT_PROMPT_INJECTION]: The skill defines a workflow for processing and editing untrusted text, such as user replies, pull request bodies, and issue descriptions.
- Ingestion points: The skill processes prose from external sources including replies, PR/issue bodies, commit messages, and documentation as defined in
SKILL.md. - Boundary markers: None are defined to separate instructions from the data being processed.
- Capability inventory: No capabilities for command execution, network access, or file system modifications are present in the skill.
- Sanitization: There are no sanitization or filtering mechanisms mentioned for the ingested text.
- Conclusion: Despite the ingestion surface, the lack of tool-based capabilities ensures that no harmful actions can be triggered by processing malicious text.
Audit Metadata