unslop
Pass
Audited by Gen Agent Trust Hub on Oct 19, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill consists entirely of natural language instructions designed to improve prose quality by removing stylistic patterns typically associated with AI-generated text. It does not request any tool permissions, perform network operations, or execute code.
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to process untrusted data sources, such as pull request bodies, documentation, and human-facing comments, which creates a potential surface for indirect prompt injection. However, the risk is negligible because the skill does not utilize any tools or capabilities that could be exploited by malicious instructions embedded in the text.
- Ingestion points: Processes user-provided prose, commit messages, and PR descriptions as specified in SKILL.md.
- Boundary markers: The instructions do not define clear delimiters or "ignore" markers for content within the processed text.
- Capability inventory: No tools (filesystem, shell, or network) are defined or requested in this skill.
- Sanitization: No input sanitization or validation logic is present.
Audit Metadata