kickoff-help
Pass
Audited by Gen Agent Trust Hub on Oct 7, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill provides instructions for the user to install components from an external repository using the command
npx skills add DietrichGebert/ponytail.- [INDIRECT_PROMPT_INJECTION]: The skill is designed to read and process other local skill files to provide accurate guidance to the user. - Ingestion points: The agent is instructed to read
SKILL.mdfiles from relative directory paths (e.g.,../kickoff/SKILL.md). - Boundary markers: There are no explicit delimiters or instructions to ignore embedded commands within the ingested files; the agent is directed to trust the referenced files over the internal mapping.
- Capability inventory: The skill's functionality is limited to information retrieval and text-based responses; it does not contain scripts or tools for file writing, network exfiltration, or automated command execution.
- Sanitization: No sanitization or validation of the content within the ingested skill files is performed.
Audit Metadata