create-bug-report
Pass
Audited by Gen Agent Trust Hub on Mar 18, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill exhibits a surface for indirect prompt injection through the ingestion of untrusted data into a process with file-writing capabilities.
- Ingestion points: The skill reads untrusted user input from $ARGUMENTS and the conversation context (SKILL.md).
- Boundary markers: Absent; the workflow does not define specific delimiters or instructions to prevent the model from obeying instructions embedded in the user-provided bug description.
- Capability inventory: The skill utilizes Bash and Write tools, which allow it to search project files and create new documents on the filesystem.
- Sanitization: Absent; the instructions do not require the agent to validate or sanitize user input before writing it to project documentation files in the .chalk/docs/ directory.
Audit Metadata