aibtc-news-scout
Pass
Audited by Gen Agent Trust Hub on Sep 18, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted data from the news network to identify beat gaps and candidate activity.
- Ingestion points: The agent reads editorial notes via
news_signalsand beat descriptions vianews_beatsto determine priorities. - Boundary markers: No explicit delimiters or instructions to ignore embedded commands are present in the processing logic.
- Capability inventory: The agent uses read-only tools to query the network and generates pitches for recruitment; it does not have autonomous write or execution capabilities over the target system.
- Sanitization: There is no evidence of sanitization or filtering of the content retrieved from external signals.
- [COMMAND_EXECUTION]: The agent executes local scripts to interact with the news platform.
- Evidence: Uses
bun run aibtc-news/aibtc-news.tsto perform various lookups and status checks. These commands target a required vendor resource.
Audit Metadata