doc-bdd-fixer
Pass
Audited by Gen Agent Trust Hub on Mar 1, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill documentation specifies the execution of the
sha256sumshell command to verify the integrity of upstream files during hash validation (FIX-H001). This is a local utility call used to compute file hashes for drift detection. - [PROMPT_INJECTION]: The skill exhibits an indirect prompt injection surface as it processes external, potentially untrusted audit and review reports to determine which file modifications to perform.
- Ingestion points: The skill reads from Audit Reports (
BDD-NN.A_audit_report_vNNN.md) and Review Reports (BDD-NN.R_review_report_vNNN.md) to drive its fix logic. - Boundary markers: No explicit boundary markers or instructions to ignore embedded commands within the input reports are implemented.
- Capability inventory: The skill has the capability to write to the file system (
Path.write_text), move files (shutil.move), create directories (os.makedirs), and execute local shell commands (sha256sum). - Sanitization: The skill lacks explicit sanitization or validation of the instructions or data extracted from the external reports before they influence file-writing or command-execution operations.
Audit Metadata