bid-optimization
Pass
Audited by Gen Agent Trust Hub on Oct 13, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes external advertising performance data from multiple sources, which presents a surface for indirect prompt injection if the data contains malicious instructions intended to influence the agent's analysis.
- Ingestion points: The
scripts/analyze-bids.pyscript ingests data fromcampaign_data.csv, Google Ads API JSON responses, and Google Sheets URLs. - Boundary markers: The documentation does not specify the use of delimiters or instructions to ignore embedded content within the ingested data.
- Capability inventory: The skill uses Python scripts to perform analysis and writes output to local files (
recommendations.json) and generates JavaScript files from templates. - Sanitization: There is no mention of sanitization, validation, or escaping logic for the external content before it is processed by the AI agent.
- [COMMAND_EXECUTION]: The workflow relies on the execution of local Python scripts (
scripts/analyze-bids.pyandscripts/generate-script.py) to perform its primary functions. These scripts are invoked via the command line to process user-provided data and generate recommendation files.
Audit Metadata