pp-foxnews

Pass

Audited by Gen Agent Trust Hub on Jun 15, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill instructs the agent to install the foxnews-pp-cli tool using npx -y @mvanhorn/printing-press install foxnews --cli-only, which downloads and executes code from the npm registry.\n- [COMMAND_EXECUTION]: The skill operates by executing bash commands, including npx for installation and the foxnews-pp-cli binary for data retrieval.\n- [PROMPT_INJECTION]: The skill exhibits an indirect prompt injection surface as it processes untrusted news content from external RSS feeds.\n
  • Ingestion points: RSS headlines and links are retrieved from https://moxie.foxnews.com and ingested into the agent context via the headlines command.\n
  • Boundary markers: Absent; the instructions do not provide delimiters or warnings for the agent to treat the external feed data as potentially untrustworthy.\n
  • Capability inventory: The skill is granted Read Bash permissions, which allows for the execution of shell commands.\n
  • Sanitization: Absent; no validation or filtering of the content retrieved from the RSS feeds is specified before processing.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 15, 2026, 02:34 AM
Security Audit — agent-trust-hub — pp-foxnews