hunk-extensions
Pass
Audited by Gen Agent Trust Hub on Oct 29, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill instructs the agent to run the command
hunk skill show hunk-extensionsto retrieve documentation. This command interfaces with the local Hunk CLI installation to provide the agent with up-to-date instructions. - [INDIRECT_PROMPT_INJECTION]: The skill uses a pointer pattern, instructing the agent to follow instructions retrieved from an external tool at runtime. This creates a surface where the agent's behavior is guided by dynamic content. Ingestion points: Command output from
hunk skill show hunk-extensions(referenced in SKILL.md). Boundary markers: Absent in the pointer file. Capability inventory: Local execution via the Hunk CLI tool. Sanitization: Not present in the skill file.
Audit Metadata