atlas-to-tickets
Pass
Audited by Gen Agent Trust Hub on Oct 22, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process data from external sources, creating a surface for embedded instructions to influence agent operations.\n
- Ingestion points: The skill fetches full bodies and comments from user-provided URLs or issue tracker references as specified in SKILL.md (Step 1: Gather context).\n
- Boundary markers: The instructions do not define explicit delimiters or instructions for the agent to treat the fetched content as data rather than instructions, potentially leading to obedience of embedded commands.\n
- Capability inventory: The skill has the ability to write multiple local files (SKILL.md Step 5) and interact with external tracker APIs (GitHub, Linear) to create issues, which could be abused if malicious instructions are processed.\n
- Sanitization: There are no documented sanitization or validation steps for the content retrieved from external sources before it is processed by the agent.
Audit Metadata