yt-hook-scripter
Pass
Audited by Gen Agent Trust Hub on Oct 6, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONDYNAMIC_EXECUTIONCOMMAND_EXECUTIONDATA_EXFILTRATION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill accepts and parses external URLs to gather video context, which creates a surface for potential indirect prompt injection if the source content contains malicious instructions.\n
- Ingestion points: External URLs are parsed using
lib/url_parser.pyin Step 1.\n - Boundary markers: There are no explicit instructions for the agent to treat parsed data as untrusted or to use delimiters to separate it from instructions.\n
- Capability inventory: The skill has access to
lib.publishfor external data transmission andyt-community-post-writerfor profile analysis.\n - Sanitization: A 'Humanizer pass' (Step 6) filters specific stylistic markers but does not provide security-focused sanitization of the ingested data.\n- [DYNAMIC_EXECUTION]: The skill invokes a local script,
lib/url_parser.py, to process and parse metadata from provided URLs.\n- [COMMAND_EXECUTION]: The instructions involve running an external command-line tool,yt-community-post-writer --mode profile, to analyze a user's previous community posts and establish a voice profile.\n- [DATA_EXFILTRATION]: The skill utilizes thelib.publishfunction to send metadata (titles, descriptions, and hooks) to external services. This is a core feature but constitutes a data transmission capability, though it is protected by a mandatory user approval step (Step 7 and 8).
Audit Metadata