to-tickets
Pass
Audited by Gen Agent Trust Hub on Sep 10, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONDATA_EXFILTRATION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data from external issue trackers and URLs which could contain malicious instructions.
- Ingestion points:
SKILL.md(Step 1) fetches content from issues and URLs provided in the conversation context. - Boundary markers: No explicit delimiters are specified for separating ingested content from the system instructions.
- Capability inventory: Writing to the local filesystem (
.scratch/directory) and interacting with external APIs (GitHub, Linear) to publish tickets. - Sanitization: The skill relies on a manual human-in-the-loop review step (Step 4: Quiz the user) to mitigate risks from ingested data before publication.
- [DATA_EXFILTRATION]: The skill performs network operations to fetch and publish data to external issue trackers such as Linear. While consistent with the skill's primary purpose, these domains fall outside the standard whitelist.
Audit Metadata