adcp-signals

Pass

Audited by Gen Agent Trust Hub on Oct 9, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill defines a workflow where the agent ingests and processes signal metadata (such as names and descriptions) from external signal providers. This data is then used to influence activation decisions, creating a vulnerability surface. 1. Ingestion points: Signal metadata fields like 'name' and 'description' returned by the get_signals tool. 2. Boundary markers: Absent; the skill instructions do not specify delimiters or instructions to ignore embedded text within the provider metadata. 3. Capability inventory: The activate_signal tool allows the agent to execute state-changing operations on external DSP platforms and sales agents. 4. Sanitization: Absent; the documentation does not describe any validation, escaping, or filtering of the metadata before processing.
  • [SAFE]: No malicious patterns such as command execution, obfuscation, or persistence mechanisms were detected. The skill consists entirely of instructional content and examples for a standard advertising protocol.
Audit Metadata
Risk Level
SAFE
Analyzed
Oct 9, 2026, 10:48 AM