di-agent-parameter-sets

Pass

Audited by Gen Agent Trust Hub on Sep 2, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill includes instructions for the agent to retrieve and update DataStage flow definitions, which creates a theoretical attack surface for instructions embedded in processed flow data.
  • Ingestion points: Flow configuration and stage property strings are ingested via retrieve_datastage_flow_code as described in SKILL.md and resources/flow_integration.md.
  • Boundary markers: The skill does not explicitly instruct the agent to use boundary markers or delimiters when interpreting content from retrieved flows.
  • Capability inventory: The agent is granted capabilities to modify project assets via update_datastage_flow, update_parameter_set, and manage_value_set (SKILL.md).
  • Sanitization: There are no explicit instructions for the agent to sanitize or validate the content retrieved from flows before using it to perform further updates. This surface is inherent to the skill's primary purpose of managing data integration flows.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 2, 2026, 06:10 PM
Security Audit — agent-trust-hub — di-agent-parameter-sets