mitm-find-pii

Pass

Audited by Gen Agent Trust Hub on Mar 23, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill is vulnerable to indirect prompt injection as it requires the agent to parse and interpret untrusted content from network traffic logs (log.txt). An attacker-controlled server could include malicious instructions in an API response which, when captured in the log, might be executed by the agent during analysis.
  • Ingestion points: The agent is explicitly instructed to analyze the content of log.txt in the current directory.
  • Boundary markers: The skill lacks delimiters or explicit instructions to the agent to treat the log content as data-only and ignore any embedded commands.
  • Capability inventory: While the skill provides analysis guidelines, the agent's own toolset (file system access, terminal execution) remains available and could be targeted by instructions hidden in the traffic dump.
  • Sanitization: The skill provides no mechanism for sanitizing or filtering the traffic data before it is processed by the agent.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 23, 2026, 09:58 PM