coding-standard

Pass

Audited by Gen Agent Trust Hub on Nov 6, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted data from the local project to generate coding standards and checklists, which could allow instructions embedded in the codebase to influence the agent's behavior.
  • Ingestion points: The skill reads README.md, source code (15-30 files), and configuration manifests (e.g., package.json, Cargo.toml) as defined in SKILL.md Section 1.
  • Boundary markers: Instructions do not specify the use of delimiters or ignore-instructions blocks to separate the analyzed content from the agent's task logic.
  • Capability inventory: The agent has the capability to perform file system write operations to the docs/ directory.
  • Sanitization: No specific sanitization, filtering, or validation of the ingested codebase content is described before processing.
Audit Metadata
Risk Level
SAFE
Analyzed
Nov 6, 2026, 06:53 AM