catalog-forecast-analyzer
Pass
Audited by Gen Agent Trust Hub on Oct 11, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to process external structured data (JSON/CSV) to produce reports, which creates a surface for indirect prompt injection where malicious instructions could be embedded in the input data to influence agent behavior.
- Ingestion points: The
run.pyscript (line 28) reads data from a user-specified input path usingPath(args.input).read_text(). - Boundary markers: There are no instructions or code-level delimiters provided to distinguish between data and instructions, or to warn the agent to ignore embedded commands.
- Capability inventory: The script possesses filesystem capabilities, including reading files, creating directories, and writing files (
read_text,write_text, andmkdir). - Sanitization: The input is loaded directly via
json.loads()without validation, filtering, or sanitization of the content for potential malicious strings.
Audit Metadata