competitor-tracker

Pass

Audited by Gen Agent Trust Hub on Jul 6, 2026

Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill uses python3 to execute local connector scripts (gdelt.py, youtube.py) found within the plugin root to collect news and social data.
  • [EXTERNAL_DOWNLOADS]: It fetches data from well-known external sources including the GDELT news index and YouTube (via RSS or API).
  • [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it ingests untrusted social media content.
  • Ingestion points: Social media post data and creator handles supplied by the user or gathered via scripts in SKILL.md.
  • Boundary markers: None provided in the analysis instructions to separate untrusted data from the agent's tasks.
  • Capability inventory: Shell command execution (Python scripts) and file write operations to the memory/ directory.
  • Sanitization: There are no documented steps for cleaning or escaping the external content before processing.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 6, 2026, 09:34 AM
Security Audit — agent-trust-hub — competitor-tracker