unslop
Pass
Audited by Gen Agent Trust Hub on Oct 2, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to process and rewrite text (commit messages, PRs, docs, etc.) which are likely provided as external input to the AI agent. This creates a surface where malicious instructions could be embedded in the text being edited.
- Ingestion points: The skill operates on text inputs provided for editing or humanization (SKILL.md).
- Capability inventory: While the skill itself is purely instructional, an agent using this skill typically has capabilities to write to files or perform Git operations as implied by the skill description.
- Boundary markers: The skill does not define specific boundary markers or warnings for the agent to ignore instructions embedded within the text it is processing.
- Sanitization: There is no evidence of sanitization or filtering of the input text to prevent instruction injection within the provided instructions.
Audit Metadata