agent-python-expert
Pass
Audited by Gen Agent Trust Hub on Oct 2, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill uses the
$ARGUMENTSplaceholder to interpolate user-provided data directly into its instruction set, which is a known surface for indirect prompt injection. - Ingestion points:
$ARGUMENTSvariable located at the end of theSKILL.mdfile. - Boundary markers: The skill does not use specific delimiters (e.g., XML tags or triple quotes) to isolate user input from the rest of the instructions.
- Capability inventory: The skill is primarily instructional and does not define high-privilege capabilities such as file system writing or remote command execution in its configuration.
- Sanitization: There are no explicit instructions or logic to sanitize or escape the interpolated content before it is processed by the agent.
Audit Metadata