file-issues
Pass
Audited by Gen Agent Trust Hub on Jul 30, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection (Category 8) due to its core functionality of ingesting and acting upon untrusted data.
- Ingestion points: The skill (in
SKILL.md) explicitly instructs the agent to read context from the current conversation, user-provided specifications, and external issue numbers or URLs, including their full bodies and comments. - Boundary markers: There are no instructions provided to the agent to use delimiters or to ignore potential instructions embedded within the external references it reads.
- Capability inventory: The agent has the capability to write local files (to the
.scratch/directory) and publish data to remote trackers like GitHub, GitLab, and Linear based on the processed input. - Sanitization: The instructions do not include any steps for sanitizing, validating, or escaping content retrieved from external sources before it is used to generate new tracker issues.
Audit Metadata