doca-dpa-hl-tracer

Pass

Audited by Gen Agent Trust Hub on Jul 28, 2026

Risk Level: SAFE
Full Analysis
  • [COMMAND_EXECUTION]: The skill documents the use of the doca_dpa_hl_tracer host-side CLI tool, providing specific instructions on capture modes and configuration flags in the TASKS.md and CAPABILITIES.md files.
  • [PROMPT_INJECTION]: The skill defines a workflow where the agent ingests and analyzes decoded trace logs, creating a potential surface for indirect instructions. * Ingestion points: The agent is instructed to read human-readable log files and parsed trace output produced by the tracer utility. * Boundary markers: Instructions mandate that the agent quote events verbatim and use specific event names, which serves as a manual delimiter for external content. * Capability inventory: The skill provides commands for capturing and decoding DPA traces using the host-side binary. * Sanitization: No explicit sanitization or filtering of the trace data is required before ingestion into the agent context.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 28, 2026, 01:22 PM
Security Audit — agent-trust-hub — doca-dpa-hl-tracer