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
python3to 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