security-guidance

Pass

Audited by Gen Agent Trust Hub on Aug 31, 2026

Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill executes git via subprocess in scripts/gitutil.py and scripts/diffstate.py to identify changed files and content. It explicitly disables git hooks during these calls to prevent execution of untrusted repository scripts.
  • [EXTERNAL_DOWNLOADS]: In scripts/ensure_agent_sdk.py, the skill uses pip to install the claude-agent-sdk from the official registry into a managed virtual environment. This is the intended behavior for bootstrapping the agentic reviewer.
  • [INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted source code into analysis prompts in scripts/llm.py and scripts/review_api.py. It includes clear delimiters and boundary instructions to the model to evaluate the data rather than follow instructions within it. 1. Ingestion points: scripts/security_reminder_hook.py. 2. Boundary markers: Present as XML-like delimiters. 3. Capability inventory: git subprocess calls and network requests to Anthropic API. 4. Sanitization: Content wrapping in blocks.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 31, 2026, 01:18 PM
Security Audit — agent-trust-hub — security-guidance