ganesh
Pass
Audited by Gen Agent Trust Hub on Apr 13, 2026
Risk Level: SAFEPROMPT_INJECTIONNO_CODE
Full Analysis
- [PROMPT_INJECTION]: The skill provides instructions to the agent to consult an external documentation source via a shortened URL (https://ishortn.ink/ganesh-official-api) which is described as changing frequently. This creates a risk of indirect prompt injection where the external content could be manipulated to execute unauthorized actions via the agent.\n
- Ingestion points: The URL in
SKILL.mdserves as a dynamic input for the agent's logic.\n - Boundary markers: Absent; there are no instructions to treat the documentation content as untrusted data.\n
- Capability inventory: The skill intends for the agent to perform network-based image uploads.\n
- Sanitization: Absent; the agent is expected to adopt the endpoints and parameters found in the documentation without validation.\n- [NO_CODE]: The skill does not provide any scripts or code, consisting exclusively of Markdown documentation.
Audit Metadata