linkedin-launch-video

Pass

Audited by Gen Agent Trust Hub on May 2, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill downloads the hyperframes package from the npm registry and fetches the GSAP animation library from the jsDelivr CDN.- [COMMAND_EXECUTION]: Uses the Bash tool to execute npx commands for initializing the HyperFrames project, linting code, and rendering the final video asset.- [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it fetches and processes untrusted content from the web to determine brand identity.
  • Ingestion points: Data enters the agent context through WebFetch operations in references/brand-identity.md and SKILL.md.
  • Boundary markers: No explicit delimiters or instructions to ignore embedded commands are used when processing fetched content.
  • Capability inventory: The skill possesses extensive capabilities including Bash command execution, file writing/editing, and network access via LinkedIn Ads and Cogny MCP tools.
  • Sanitization: There is no evidence of sanitization or validation of the external content before it is used to influence the agent's creative or technical output.
Audit Metadata
Risk Level
SAFE
Analyzed
May 2, 2026, 06:43 AM
Security Audit — agent-trust-hub — linkedin-launch-video