review-prompt
Pass
Audited by Gen Agent Trust Hub on Oct 17, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONNO_CODE
Full Analysis
- [SAFE]: The skill is purely instructional, providing a structured methodology for evaluating the quality and provenance of prompt lines. It does not include any executable code, scripts, or external dependencies.
- [INDIRECT_PROMPT_INJECTION]: The skill involves processing user-provided prompts (input text or file content), which is an ingestion point for untrusted data. However, the skill is constrained to read-only diagnostics ('it never edits the prompt'), and it lacks dangerous capabilities like shell execution, file writing, or network access that could be exploited by an injection.
- Ingestion points: Analyzes prompts provided via file paths or inline text as described in
SKILL.md. - Boundary markers: The instructions do not define specific delimiters for the input text, though the output follows a structured markdown report format.
- Capability inventory: No subprocess calls, file system modifications, or network operations are present in the skill definition.
- Sanitization: There is no explicit sanitization or filtering of the input prompt content mentioned.
- [NO_CODE]: The skill consists entirely of markdown instructions and metadata, with no associated scripts, shell commands, or binaries.
Audit Metadata