portainer-ce-2-39
Pass
Audited by Gen Agent Trust Hub on Mar 31, 2026
Risk Level: SAFEPROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [PROMPT_INJECTION]: The skill provides instructions for reading data from external Portainer environments, creating a potential surface for indirect prompt injection where malicious instructions could be embedded in API responses.
- Ingestion points: Untrusted data enters the agent context via endpoints such as
/stacks/{id}/file,/kubernetes/{id}/events, and/custom_templatesas described in SKILL.md. - Boundary markers: The instructions do not specify the use of delimiters or 'ignore' instructions when the agent processes these responses.
- Capability inventory: The skill utilizes
curlfor all operations and has the capability to modify infrastructure through various POST and PUT endpoints. - Sanitization: No sanitization, escaping, or validation of the content returned from the API is mentioned.
- [COMMAND_EXECUTION]: The skill includes several
curlcommand examples for interacting with the API. These are documented safely using placeholders (e.g.,<portainer>,<password>) for hostnames and credentials, ensuring no sensitive data is hardcoded.
Audit Metadata