specrail-release-note
Pass
Audited by Gen Agent Trust Hub on Jul 22, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill processes untrusted external data from pull requests, commits, and issues to draft release notes. This content could contain malicious instructions (indirect prompt injection) designed to influence the agent's output.
- Ingestion points: PR content, linked issues, commits, and verification evidence in SKILL.md.
- Boundary markers: Absent; there are no instructions to ignore embedded commands within the ingested data.
- Capability inventory: Executes a local verification script (
checks/route_gate.py) via the shell. - Sanitization: No explicit validation or escaping of the input data is mentioned.
- [COMMAND_EXECUTION]: The skill instructs the agent to execute a local Python script (
checks/route_gate.py) to verify the state of PRs and issues. While this is a common workflow for development skills, it involves shell command execution using user-provided arguments like issue and PR numbers.
Audit Metadata