lexicon
Pass
Audited by Gen Agent Trust Hub on Oct 8, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data from the local project environment which may contain hidden instructions intended to influence the agent's behavior during audits or naming critiques.
- Ingestion points: The skill reads
LEXICON.md,TERMS.md,GLOSSARY.md,CONTEXT.md,README.md, specs, schemas, APIs, and core codebase files (e.g.,src/types.ts) as described in the 'Load', 'Survey', and 'Scan' workflows inSKILL.md. - Boundary markers: The instructions lack explicit boundary markers or delimiters to separate instructions from the data being analyzed.
- Capability inventory: The skill is designed to read file contents and propose or apply file system writes (edits) to the codebase based on its analysis.
- Sanitization: There is no automated sanitization mentioned; however, the 'Review and resolution procedure' emphasizes user authority, requiring explicit user approval for any 'Tier 2' or 'Tier 3' changes and summarizing all proposed modifications.
Audit Metadata