contacts
Pass
Audited by Gen Agent Trust Hub on Sep 16, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONDATA_EXFILTRATIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill utilizes the browser, google-search, and x-api tools to fetch data from various external sources including general web pages and social media profiles.
- [DATA_EXFILTRATION]: Extracted contact details, including names, roles, and social media identifiers, are transmitted to external search providers for enrichment and indexed to a Typesense instance. It also accesses sensitive local directories including ~/Vault/Contacts/ and ~/Code/joelhooks/egghead-roam-research/.
- [COMMAND_EXECUTION]: Provides embedded Python and Bash scripts intended to search and parse local EDN data files within the user's workspace.
- [INDIRECT_PROMPT_INJECTION]: Processes untrusted data from web crawls, podcast transcripts, and social media posts, creating a surface for indirect prompt injection where malicious instructions in the source material could influence the LLM's enrichment output.
Audit Metadata