w-release
Pass
Audited by Gen Agent Trust Hub on Sep 18, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONNO_CODE
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and analyze untrusted external data, specifically pull request diffs and repository documentation, which presents a surface for indirect prompt injection attacks.\n
- Ingestion points: The agent is instructed to read pull request diffs (feature PR or release PR) and repository release documentation mentioned in
SKILL.md.\n - Boundary markers: Absent. The instructions do not specify delimiters or guidelines to separate external data from the agent's logic.\n
- Capability inventory: The skill includes no scripts, tool invocations, or network access; it relies purely on the agent's textual analysis.\n
- Sanitization: Absent. There are no instructions to sanitize or validate the content of the repository files before processing.
Audit Metadata