write-issue
Pass
Audited by Gen Agent Trust Hub on May 15, 2026
Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
- [COMMAND_EXECUTION]: The skill provides instructions for an agent to execute a local CLI utility named
bdto manage issue trackers. It uses templates to populate command-line arguments like--titleand--descriptionusing information extracted from conversation history. This is the core functionality of the skill and is consistent with its stated purpose. - [PROMPT_INJECTION]: The skill possesses a surface for indirect prompt injection as it processes untrusted user data from conversation context.
- Ingestion points: Conversation context is ingested to populate the issue templates defined in
SKILL.md. - Boundary markers: There are no explicit boundary markers or instructions for the agent to ignore potentially malicious instructions embedded in the ingested data.
- Capability inventory: The skill enables the execution of the
bdshell command. - Sanitization: There are no explicit sanitization, validation, or shell-escaping instructions provided for the data interpolated into the command-line arguments.
Audit Metadata