ste-clarity

Pass

Audited by Gen Agent Trust Hub on Oct 29, 2026

Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill executes a bundled Python linter script to validate technical prose. The script, scripts/ste_lint.py, is built using only Python standard libraries and performs analysis locally without network interaction.
  • [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted text input for technical rewriting, which represents an attack surface for indirect prompt injection. Ingestion Point: Arbitrary user-provided technical prose processed in SKILL.md. Boundary Markers: Absent. Capability Inventory: Local execution of a Python-based regex linter. Sanitization: Absent. The risk is mitigated by the highly constrained nature of the rewriting task itself.
  • [SAFE]: No malicious patterns or security risks were identified. The skill instructions specifically advise against hardcoding API keys and use standard shell piping for text validation. All external URLs point to legitimate technical documentation and established open-source repositories.
Audit Metadata
Risk Level
SAFE
Analyzed
Oct 29, 2026, 03:18 PM