ai-mode-optimization
Pass
Audited by Gen Agent Trust Hub on Sep 26, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill analyzes untrusted data from external sources, such as search engine results (SERPs) and target web pages, to map question spaces and audit content coverage.
- Ingestion points: Fetches web content and People Also Ask (PAA) data from SERPs using
webfetchanddfs_client.py(referenced in SKILL.md). - Boundary markers: Not present; the skill does not explicitly define delimiters to separate instructions from the crawled content during the mapping and audit process.
- Capability inventory: The skill can write report files to the local file system (
AI-MODE-<topic>-<date>.md) and execute Python scripts (dfs_client.py,report_publish.py). - Sanitization: No evidence of sanitizing external data before it is incorporated into the analysis or subsequent reports.
- [COMMAND_EXECUTION]: The skill uses a subprocess to run local Python scripts for data collection and report generation.
- Evidence: Executes
python scripts/dfs_client.pywith keywords and limits to pull live data from external sources. - Evidence: Executes
python scripts/report_publish.pyto transform generated reports into branded HTML and PDF formats.
Audit Metadata