loop-triage
Pass
Audited by Gen Agent Trust Hub on Oct 12, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONNO_CODE
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data from multiple external sources, creating an attack surface for indirect prompt injection.
- Ingestion points: The skill instructions specify reading recent CI failures, Open PRs, Open issues, commit messages, and Slack/chat threads (SKILL.md).
- Boundary markers: There are no instructions provided to the agent to use delimiters or to ignore instructions that might be embedded within the external data being triaged.
- Capability inventory: The skill is designed to write structured output to a state file or a Linear board, which implies the use of file-system or API-based tools.
- Sanitization: The skill lacks instructions for sanitizing, escaping, or validating the ingested content before it is processed or used to generate actions.
- [NO_CODE]: The provided skill contains only natural language instructions and YAML frontmatter. It does not include any executable scripts, binary files, or automated shell commands.
Audit Metadata