ste100
Pass
Audited by Gen Agent Trust Hub on Nov 2, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill's workflow involves executing an included Python script (
scripts/ste_check.py) to lint text for rule compliance. The script is restricted to the standard library, using regex to perform static analysis on text content without network or sensitive file access.\n- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted user-provided text as its primary function, creating an injection surface.\n - Ingestion points: Arbitrary text from docs, READMEs, and user prompts processed via SKILL.md instructions.\n
- Boundary markers: No specific delimiters are mandated for user content, but the skill follows strict rewrite rules that prioritize fact preservation.\n
- Capability inventory: Limited to text generation and execution of the included local analysis script; lacks network or system-level write permissions.\n
- Sanitization: The provided analysis script uses regex to strip markdown code blocks and frontmatter to avoid processing non-prose content.
Audit Metadata