tao-route-visual-changenet-samples

Warn

Audited by Gen Agent Trust Hub on Sep 17, 2026

Risk Level: MEDIUMDATA_EXFILTRATIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [DATA_EXFILTRATION]: The hooks/routing-package.sh hook automatically copies sensitive files from the local environment into the skill's output directory. This includes the agent's project configuration (.claude/settings.json, .claude/settings.local.json) and session transcripts. While intended for workflow reproducibility, this behavior exposes sensitive settings and conversation history within the generated results artifacts.
  • [INDIRECT_PROMPT_INJECTION]: The skill ingests data from external sources (gaps_parquet and source_pool_csv) without applying security boundaries or sanitization. This creates an attack surface where maliciously crafted data could influence the agent's analysis or report generation.
  • Ingestion points: Untrusted parquet and CSV files specified by the user as input to the routing process.
  • Boundary markers: No delimiters or instructions are used to isolate untrusted data from the agent's execution context.
  • Capability inventory: The skill uses Bash to execute Python scripts that process the data and Read to access the filesystem.
  • Sanitization: No filtering or escaping is performed on the ingested labels or metadata before they are included in the generated Routing_Report.md.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Sep 17, 2026, 02:56 AM
Security Audit — agent-trust-hub — tao-route-visual-changenet-samples