hyperframes-instagram-caption

Pass

Audited by Gen Agent Trust Hub on Aug 21, 2026

Risk Level: SAFEPROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
  • [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection through its ingestion of external data.
  • Ingestion points: It reads content from topics/<주제>/index.html to extract caption data (SKILL.md).
  • Boundary markers: The instructions lack explicit delimiters or instructions to ignore embedded commands within the ingested content.
  • Capability inventory: The skill has the ability to write to the file system (creating instagram-caption-ko.txt) and execute shell utilities (wc, head).
  • Sanitization: No logic is provided to filter or sanitize the content extracted from the HTML files before it is processed by the agent.
  • [COMMAND_EXECUTION]: The skill utilizes standard terminal utilities for output verification.
  • Evidence: It specifies the use of wc -c to check character limits and head -c to verify the length of the hook section (SKILL.md).
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 21, 2026, 06:41 PM
Security Audit — agent-trust-hub — hyperframes-instagram-caption