specrail-review-pr

Pass

Audited by Gen Agent Trust Hub on Jul 22, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill executes local Python scripts checks/route_gate.py and checks/review_json_gate.py. These scripts are used for routing checks and artifact validation within the repository context.
  • [PROMPT_INJECTION]: The skill processes untrusted external data which creates an indirect prompt injection surface.
  • Ingestion points: Step 1 involves reading pull requests, linked issues, product/tech specs, and local diffs, which are all potentially attacker-controlled.
  • Boundary markers: There are no explicit instructions or delimiters to isolate untrusted data from the agent's internal instructions or to warn the agent to ignore instructions embedded within the processed content.
  • Capability inventory: The skill possesses the capability to execute shell commands via Python scripts (Steps 3 and 7) and perform file reads.
  • Sanitization: Input parameters such as <issue-number> and <pr-number> are derived from external data and interpolated into shell commands without explicit sanitization or validation logic provided in the instructions.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 22, 2026, 09:48 AM
Security Audit — agent-trust-hub — specrail-review-pr