pestel-analysis
Pass
Audited by Gen Agent Trust Hub on Oct 25, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it interpolates unvalidated user input directly into prompts for subagents.\n
- Ingestion points: The
SUBJECT,GEOGRAPHY,HORIZON, andCONTEXTinputs defined inSKILL.mdare directly inserted into the instructions for the parallel analyst subagents.\n - Boundary markers: The prompt template in
SKILL.mddoes not use explicit delimiters (such as XML tags or triple quotes) to encapsulate the user-supplied data, making it easier for an attacker to break out of the intended context.\n - Capability inventory: The skill has the capability to write files to the local working directory, which could be abused if an injection attack successfully manipulates the file saving logic.\n
- Sanitization: There is no evidence of input sanitization or validation to ensure the provided context does not contain malicious instructions aimed at overriding the agent's behavior.
Audit Metadata