climate-tech-advisor
Pass
Audited by Gen Agent Trust Hub on Nov 18, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: Analysis of the skill instructions, metadata, and the
carbon_impact_estimator.pyscript reveals no evidence of malicious patterns, obfuscation, or unauthorized access to sensitive system resources. The skill functions as a strategic advisor as described. - [INDIRECT_PROMPT_INJECTION]: The skill exhibits a vulnerability surface for indirect prompt injection as it processes untrusted user-supplied business descriptions.
- Ingestion points: User input provided in
business_description.txt(or a similar provided file) is ingested by thecarbon_impact_estimator.pyscript and its output is then used by the agent for classification. - Boundary markers: Absent. The instructions do not specify the use of delimiters or specific "ignore embedded instructions" warnings when handling the input file.
- Capability inventory: The skill is capable of reading local files and executing its own internal Python script. It lacks high-privilege capabilities such as network exfiltration, arbitrary command execution, or system-level modifications.
- Sanitization: Absent. While the Python script uses regex for classification, it does not perform sanitization of the input text to prevent it from influencing the agent's behavior during processing.
Audit Metadata