qrspi-create-research-questions
Pass
Audited by Gen Agent Trust Hub on Jun 21, 2026
Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill instructs the agent to use the GitHub CLI (
gh) and Linear CLI/API to fetch ticket data. These operations are essential to the skill's stated purpose of ticket analysis and are conducted using standard project-management tools.\n- [EXTERNAL_DOWNLOADS]: The skill includes instructions to generate HTML presentation decks using thereveal.jslibrary fetched via a CDN. This is a well-known service and the reference is neutral and consistent with the feature's documentation.\n- [PROMPT_INJECTION]: The skill processes untrusted external content from ticket systems, which presents a surface for indirect prompt injection.\n - Ingestion points: Ticket titles, bodies, and comments are fetched from GitHub or Linear and processed by the agent.\n
- Boundary markers: There are no explicit delimiters or instructions to treat the ingested ticket content as untrusted data that should not be followed as instructions.\n
- Capability inventory: The agent can read and write files within the project structure and execute CLI tools.\n
- Sanitization: The skill does not describe any specific sanitization or filtering of the fetched ticket content before it is used to generate research questions.
Audit Metadata