aeon-narrative-tracker
Pass
Audited by Gen Agent Trust Hub on Sep 24, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill is installed from the author's repository at
github.com/BankrBot/skills. This aligns with the expected vendor behavior. - [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and summarize data from external, untrusted sources which could contain malicious instructions.
- Ingestion points: Data is pre-fetched from X (Twitter) search results and broader web search platforms like DefiLlama and Kaito (SKILL.md).
- Boundary markers: The instructions do not specify any delimiters or safety guidelines to help the agent distinguish between narrarive data and embedded instructions.
- Capability inventory: The skill is primarily focused on generating narrative reports and does not appear to possess high-risk capabilities such as arbitrary command execution or file system modification.
- Sanitization: There are no documented steps for sanitizing or filtering the content retrieved from social media or web sources.
Audit Metadata