youtube-title
Pass
Audited by Gen Agent Trust Hub on Nov 6, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted data from a local knowledge base (Obsidian vault or Markdown notes) to ground its title generation logic. This data could contain malicious instructions designed to manipulate the agent's output or behavior.
- Ingestion points: Local Markdown files and Obsidian vault notes (SKILL.md).
- Boundary markers: Absent. The instructions do not define delimiters or specify that the agent should ignore instructions found within the vault content.
- Capability inventory: The skill has the capability to write back to files (recording rules/titles) and execute local scripts.
- Sanitization: No sanitization or validation of the vault content is performed before processing.
- [COMMAND_EXECUTION]: The skill instructs the agent to run a shell command (
python3 skills/youtube-description/scripts/youtube_check.py) using the generated title as an argument. If the title generation process is compromised by indirect prompt injection from the local notes, this could lead to command injection vulnerabilities depending on how the title is handled by the shell.
Audit Metadata