filing-ai-proposed-tickets
Pass
Audited by Gen Agent Trust Hub on Oct 27, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill establishes an attack surface where untrusted data from a Linear workspace could influence agent behavior.
- Ingestion points: The agent retrieves existing ticket titles, descriptions, and statuses using the
mcp__plugin_lt-dev_linear__list_issuesandget_issuetools as part of its duplicate search process described in SKILL.md. - Boundary markers: The instructions do not define specific delimiters or include instructions for the agent to ignore potentially malicious directions embedded within the ticket data it reads.
- Capability inventory: Across the SKILL.md file, the agent is granted capabilities to create and update tickets via
mcp__plugin_lt-dev_linear__save_issueand create new labels viamcp__plugin_lt-dev_linear__save_issue_label. - Sanitization: No sanitization, validation, or escaping procedures are specified for the external ticket content before the agent evaluates it to determine if a new proposal is a duplicate.
Audit Metadata