humanize-plus
Pass
Audited by Gen Agent Trust Hub on Aug 28, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes user-supplied articles as its primary input for polishing and analysis. This creates an inherent surface for indirect prompt injection, where malicious instructions could be embedded within the text provided by the user to attempt to override the agent's editing rules. However, the risk is negligible as the skill lacks high-impact capabilities such as network access, file system writes, or shell execution.
- Ingestion points: The skill ingests untrusted text provided by the user in the
SKILL.mdprocessing flow. - Boundary markers: No explicit delimiters or boundary markers are defined to separate user content from system instructions.
- Capability inventory: The skill is limited to text analysis and generation; it contains no subprocess calls, file operations, or network requests.
- Sanitization: No specific input sanitization or filtering of external content is implemented.
Audit Metadata