sync-docs

Pass

Audited by Gen Agent Trust Hub on May 17, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill requires the execution of shell commands such as git diff, ls, and grep to determine the branch state, discover the documentation layout, and scan file contents for symbol references.
  • [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it ingests and analyzes untrusted data from the repository's source code (src/) and documentation (docs/). Malicious instructions embedded within these files could potentially influence the agent's behavior during the scanning and reporting phases.
  • Ingestion points: File contents from src/**/*.ts, package.json, and all markdown files within the docs/ directory.
  • Boundary markers: Absent. The workflow does not specify the use of delimiters or instructions to ignore embedded prompts within the processed data.
  • Capability inventory: Includes shell command execution (git, ls, grep) and file system read access.
  • Sanitization: Absent. The skill instructions do not include steps to sanitize or escape the content read from files before the agent processes it.
Audit Metadata
Risk Level
SAFE
Analyzed
May 17, 2026, 11:49 PM
Security Audit — agent-trust-hub — sync-docs