tipkit
Pass
Audited by Gen Agent Trust Hub on Jul 5, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSPROMPT_INJECTIONNO_CODE
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill's main instruction file (
SKILL.md) directs the agent to fetch additional documentation from an external mirror athttps://sosumi.aiif the required information is not found in the local reference files.\n- [PROMPT_INJECTION]: The instruction to ingest and process documentation from a third-party domain creates a potential surface for indirect prompt injection.\n - Ingestion points:
SKILL.mdinstructs the agent to access documentation viahttps://sosumi.ai/documentation/tipkit/...when needed.\n - Boundary markers: Absent; there are no instructions to use delimiters or ignore instructions embedded in the external content.\n
- Capability inventory: The skill is documentation-only and does not include any scripts or tools that perform command execution, file system modifications, or network operations.\n
- Sanitization: Absent; the skill does not define methods to validate or sanitize the incoming markdown content.\n- [NO_CODE]: The skill consists entirely of markdown documentation and YAML configuration; no executable code (Python, JavaScript, or shell scripts) is included in the package.
Audit Metadata