mitm-find-referer
Pass
Audited by Gen Agent Trust Hub on Sep 18, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill instructs the agent to process
log.txt, which contains untrusted network traffic data captured from external websites. - Ingestion points: The agent reads and processes the contents of
log.txtlocated in the current directory. - Boundary markers: The instructions do not define specific delimiters or include warnings to ignore instructions that might be embedded within captured traffic logs.
- Capability inventory: The skill itself describes analysis steps; no automated scripts or network operations are triggered directly by the skill content.
- Sanitization: There is no evidence of filtering or validation of the log data before it is presented to the agent for analysis.
Audit Metadata