review-changes

Pass

Audited by Gen Agent Trust Hub on Nov 13, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTIONNO_CODE
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill processes external code changes and function definitions through tools like detect_changes_tool and query_graph_tool. This involves ingesting untrusted data which could potentially contain instructions intended to influence the agent's review logic or output.
  • Ingestion points: detect_changes_tool and query_graph_tool defined in SKILL.md process user-provided code changes.
  • Boundary markers: The instructions do not define specific delimiters or instructions to ignore embedded prompts within the code being reviewed.
  • Capability inventory: The skill is limited to graph querying and analysis tools (detect_changes_tool, get_affected_flows_tool, query_graph_tool, get_impact_radius_tool); it does not demonstrate capabilities for network exfiltration or direct file system modification.
  • Sanitization: There is no explicit mention of sanitizing or escaping the content retrieved from the code analysis tools before it is processed by the agent.
  • [NO_CODE]: The skill consists exclusively of instructional markdown and YAML configuration. No executable scripts (Python, JavaScript, Shell) are included in the skill definition.
Audit Metadata
Risk Level
SAFE
Analyzed
Nov 13, 2026, 04:47 AM