writing-linear-comments
Pass
Audited by Gen Agent Trust Hub on Oct 27, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data from external sources (Linear issues and comments) which could contain malicious instructions designed to subvert agent behavior.
- Ingestion points: Data is ingested through
mcp__plugin_lt-dev_linear__get_issue,mcp__plugin_lt-dev_linear__get_document, andmcp__plugin_lt-dev_linear__list_comments(SKILL.md). - Boundary markers: The instructions do not define explicit boundary markers or delimiters (e.g., XML tags or "ignore instructions" warnings) for the ingested content, although they emphasize specific structured blocks for output.
- Capability inventory: The agent has the capability to write and modify content on the platform using
mcp__plugin_lt-dev_linear__save_comment,mcp__plugin_lt-dev_linear__save_document, andmcp__plugin_lt-dev_linear__create_attachment_from_upload(SKILL.md). - Sanitization: The skill references a related
unslopskill (SKILL.md) to be used as a prose pass before posting content, which acts as a manual or automated review step to sanitize outputs.
Audit Metadata