poteto-agent
Pass
Audited by Gen Agent Trust Hub on Sep 30, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill instructions require the agent to read and process the full content of a sibling skill file located at
../poteto-mode/SKILL.mdto maintain operational context. - Ingestion points: The agent is explicitly instructed in both the metadata description and the instruction body to read the file
../poteto-mode/SKILL.mdbefore performing any work. - Boundary markers: The instructions do not include specific delimiters or 'ignore' warnings for the data ingested from the sibling file.
- Capability inventory: The skill does not define or utilize any high-risk capabilities such as network operations, file system writing, or arbitrary command execution.
- Sanitization: There is no evidence of sanitization or filtering logic applied to the content read from the external file path.
Audit Metadata