tech-video-metadata

Pass

Audited by Gen Agent Trust Hub on Mar 10, 2026

Risk Level: SAFEPROMPT_INJECTIONNO_CODE
Full Analysis
  • [NO_CODE]: The skill consists exclusively of markdown documentation and reference files. It does not include any Python scripts, Node.js code, shell scripts, or other executable components.
  • [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection due to its core functionality of ingesting and analyzing untrusted data from external sources. Ingestion points: In references/content-analysis.md, the workflow involves reading and analyzing content from user-provided article URLs and local markdown files. Boundary markers: There are no explicit instructions or delimiters defined in the reference files to isolate external content or prevent the agent from following instructions embedded within that content. Capability inventory: The skill's capabilities are limited to text analysis, summarization, and metadata generation; it does not possess capabilities for file-system modification or unauthorized network access. Sanitization: No mechanisms for sanitizing, filtering, or validating external input are specified in the provided instructions.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 10, 2026, 05:05 PM