cortex
Pass
Audited by Gen Agent Trust Hub on Jun 17, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill processes untrusted user data in a way that could allow for indirect prompt injection attacks.
- Ingestion points: External data is ingested via the
{{args}}template variable withinSKILL.md. - Boundary markers: The skill does not use delimiters (such as XML tags or unique markers) or specific instructions to isolate the user-provided arguments from the agent's core instructions.
- Capability inventory: The agent has access to sensitive tools including
Bash,Write,WebFetch, andWebSearchthrough itsallowed-toolsconfiguration. - Sanitization: There is no evidence of input validation or content filtering before the interpolated data is used to invoke sub-skills.
Audit Metadata