sync-context

Pass

Audited by Gen Agent Trust Hub on Aug 25, 2026

Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill executes local Node.js utility scripts (e.g., .agents/scripts/precheck.mjs, .agents/scripts/spec-files.mjs) to perform pre-checks, query context, and validate file formatting. These scripts are project-internal maintenance tools.
  • [COMMAND_EXECUTION]: The skill uses standard Git commands (git status, git diff) to identify changed files within the local workspace for documentation synchronization.
  • [DATA_EXPOSURE]: The skill reads local repository documentation files in .agents/docs/CONTEXT/ and processes Git output. These operations are limited to the local environment and are necessary for the skill's stated purpose.
  • [INDIRECT_PROMPT_INJECTION]: The skill handles untrusted data from repository files to update its context index.
  • Ingestion points: Processes Git diff outputs and file content within the .agents/docs/CONTEXT/ directory (SKILL.md).
  • Boundary markers: Utilizes interactive user prompts (交互式提问) to resolve ambiguities and requires a parse command for structure validation.
  • Capability inventory: Performs file write/delete operations and executes local maintenance scripts.
  • Sanitization: Mandates structural validation via a local parsing script before any content is processed or updated.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 25, 2026, 05:36 AM
Security Audit — agent-trust-hub — sync-context