write-coding-standards-from-file

Pass

Audited by Gen Agent Trust Hub on Sep 15, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill fetches content from a large list of external technical documentation and style guide URLs (e.g., Microsoft, Google, GitHub, Python.org, and various community-run style guides) to use as context for generating standards. While most targets are well-known technical references, the skill performs network operations to these sites when the fetchStyleURL parameter is enabled.
  • [COMMAND_EXECUTION]: The skill performs file system operations, including creating new files (e.g., STYLE.md, CODING_STANDARDS.md), writing new test files when addStandardsTest is true, and modifying the existing README.md file by inserting generated content at various positions.
  • [INDIRECT_PROMPT_INJECTION]: The skill possesses an attack surface for indirect prompt injection:
  • Ingestion points: The skill reads and processes the content of local files and folders provided in ${fileName} and ${folderName}, as well as external content fetched from style guide URLs.
  • Boundary markers: None are specified to distinguish between the skill's instructions and the untrusted content being analyzed.
  • Capability inventory: The skill has the capability to write new files to the repository, modify existing documentation (README.md), and perform network fetches.
  • Sanitization: No sanitization or validation of the analyzed file content is mentioned. Maliciously crafted source code could potentially influence the agent's logic during the analysis and generation phase.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 15, 2026, 06:49 AM
Security Audit — agent-trust-hub — write-coding-standards-from-file