apply-ontology-patch
Pass
Audited by Gen Agent Trust Hub on Jul 24, 2026
Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
- [COMMAND_EXECUTION]: The skill executes the
graphifyCLI tool to perform data validation and entity patching.\n- [COMMAND_EXECUTION]: It uses user-provided file paths as arguments for shell commands. While this introduces a potential injection surface, the interactive nature of the skill and the human-in-the-loop approval process provide sufficient oversight.\n- [PROMPT_INJECTION]: The skill processes external data via patch files, representing an indirect prompt injection surface.\n - Ingestion points: External file content is read during the
validateandapplysteps (SKILL.md).\n - Boundary markers: None present to delimit untrusted file content.\n
- Capability inventory: The skill can perform file system mutations via the
graphify patch applycommand (SKILL.md).\n - Sanitization: The potential for malicious instructions in patch files is mitigated by a mandatory multi-step process: automated validation, a dry-run output preview, and a strict requirement for explicit human approval before the final application of the patch.
Audit Metadata