jab-jab-right-hook-vaynerchuk
Pass
Audited by Gen Agent Trust Hub on Oct 9, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes user-supplied social media posts, campaign plans, and content calendars to provide critiques and platform adaptations. This creates a surface where a malicious user could potentially embed instructions within the text to be reviewed in an attempt to influence the agent's behavior. However, the skill does not possess high-risk capabilities such as network access, system command execution, or file writing, which effectively mitigates the potential impact of such an attack.\n
- Ingestion points: User-provided post text, assets, and campaign goals as defined in the 'Query Response Framework' in
SKILL.md.\n - Boundary markers: The skill does not specify the use of clear delimiters or instructions to ignore embedded commands within the user-supplied data.\n
- Capability inventory: No subprocess calls, evaluation of dynamic code, network operations, or file system modifications are present in the skill files.\n
- Sanitization: There are no documented procedures for sanitizing or validating the input text before it is processed by the agent.\n- [EXTERNAL_DOWNLOADS]: The documentation mentions an installation command using a CLI tool that references the author's public repository. This is a standard installation method for the platform and correctly points to the vendor's own resources based on the provided author context.
Audit Metadata