to-tickets-agentic
Pass
Audited by Gen Agent Trust Hub on Aug 19, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill processes untrusted external data from project specifications, issue bodies, and content from provided URLs, which creates a surface for indirect prompt injection.\n
- Ingestion points: The agent reads full bodies and comments from issues and specs, as well as the content of provided external URLs, during the context gathering phase.\n
- Boundary markers: The skill instructions do not establish clear delimiters or specify that the agent should ignore instructions embedded within the external data it ingests.\n
- Capability inventory: The agent has the capability to write files to the local filesystem (under the .scratch/ directory) and interact with external issue trackers to create or modify tickets based on the processed data.\n
- Sanitization: There are no instructions for sanitizing, validating, or filtering the content retrieved from external sources before it is interpreted by the agent.
Audit Metadata