aj-stock-analysis

Pass

Audited by Gen Agent Trust Hub on Feb 26, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The scripts/news_fetcher.py script connects to well-known technology services, specifically Google News and Bing News, to retrieve RSS feeds for sentiment analysis. This is a standard operation for the skill's stated purpose.
  • [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it fetches untrusted headlines and summaries from the web and includes them in reports generated by the agent.
  • Ingestion points: External news data is ingested via scripts/news_fetcher.py from public RSS feeds.
  • Boundary markers: The skill lacks explicit delimiters or instructions to the agent to disregard commands embedded within the retrieved news text.
  • Capability inventory: The skill has the capability to execute Python scripts, write files to the local system, and access the network.
  • Sanitization: There is no evidence of sanitization or filtering of the fetched news content before it is processed by the agent to create the final_report.md.
  • [DATA_EXPOSURE]: The skill manages its API credentials by reading from ~/.aj-skills/.env. This is a vendor-specific configuration path consistent with the author's namespace and represents standard practice for local CLI tools.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 26, 2026, 10:47 AM