ajtbd-job-graph
Pass
Audited by Gen Agent Trust Hub on Mar 5, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill possesses a surface for indirect prompt injection by processing external data. * Ingestion points: The skill reads from the .ajtbd/segments.md file to gather context. * Boundary markers: There are no delimiters or instructions to ignore potential commands within the file data. * Capability inventory: The skill has permissions for Bash, Write, Glob, and WebSearch. * Sanitization: No validation or filtering is applied to the data read from the local file system.
- [SAFE]: No malicious obfuscation, hardcoded credentials, or persistence mechanisms were detected.
- [COMMAND_EXECUTION]: While the Bash tool is listed in the allowed tools, the instructions do not define any specific shell commands or script execution logic.
Audit Metadata