mitm-security-audit
Pass
Audited by Gen Agent Trust Hub on Sep 18, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to process and analyze untrusted data from network traffic logs.
- Ingestion points: The agent is directed to read
log.txt(referenced in SKILL.md), which contains raw HTTP requests and responses from external sources. - Boundary markers: The instructions lack specific delimiters or "ignore instructions" warnings to differentiate the traffic data from the agent's core instructions.
- Capability inventory: The skill has the capability to read local files and perform complex analysis to extract sensitive data and vulnerabilities.
- Sanitization: There is no evidence of sanitization or filtering applied to the captured traffic before the agent processes it, leaving it susceptible to instructions embedded within the traffic content.
Audit Metadata