discover-containers

Pass

Audited by Gen Agent Trust Hub on Feb 15, 2026

Risk Level: LOWPROMPT_INJECTION
Full Analysis
  • [Indirect Prompt Injection] (LOW): The skill instructs the agent to read external local files, creating a surface where instructions embedded in those files could influence agent behavior.
  • Ingestion points: Multiple files under <cc-polymath-root>/skills/containers/, specifically INDEX.md and individual skill files (e.g., container-security.md).
  • Boundary markers: Absent; the skill does not provide delimiters to isolate the ingested content.
  • Capability inventory: The skill utilizes local file reading to load additional instructions and workflow details.
  • Sanitization: Absent; the content from the files is directly incorporated into the agent's context.
  • [Data Exfiltration] (SAFE): No access to sensitive files or network exfiltration attempts were found.
  • [Remote Code Execution] (SAFE): No download or execution of remote scripts or unverified packages was detected.
Audit Metadata
Risk Level
LOW
Analyzed
Feb 15, 2026, 11:23 PM