tea-get-issue
Pass
Audited by Gen Agent Trust Hub on Aug 11, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill instructs the agent to execute the
teaCLI tool to retrieve issue information from a Forgejo instance. - [PROMPT_INJECTION]: The skill is vulnerable to indirect prompt injection as it ingests and processes untrusted data from external Forgejo issues.
- Ingestion points: The output of the
tea issue <issue-id>command, as defined inSKILL.md. - Boundary markers: Absent; the instructions do not include delimiters or warnings to treat the fetched issue content as non-instructional data.
- Capability inventory: The agent has access to the
teaCLI tool and standard agent capabilities. - Sanitization: Absent; the skill does not specify any validation, filtering, or escaping of the content retrieved from Forgejo.
Audit Metadata