social-media

Pass

Audited by Gen Agent Trust Hub on Mar 17, 2026

Risk Level: SAFENO_CODE
Full Analysis
  • [SAFE]: No malicious logic, obfuscation, or unauthorized data exposure patterns were detected within the documentation or instructional prompts.
  • [NO_CODE]: The skill consists entirely of Markdown files (README.md and SKILL.md) providing instructions to the agent. It does not include any Python, JavaScript, or shell scripts.
  • [PROMPT_INJECTION]: The skill defines a surface for indirect prompt injection by instructing the agent to ingest and transform content from external URLs or pasted text (File: SKILL.md).
  • Ingestion points: Capability 3 'Repurposing' directs the agent to process content from user-provided URLs and transcripts.
  • Boundary markers: The instructions do not define specific delimiters for separating user-provided source material from the agent's instructions.
  • Capability inventory: As the skill contains no executable code, it lacks capabilities for subprocess execution, file system access, or network calls beyond text retrieval.
  • Sanitization: No validation or sanitization of the input content is specified.
  • Justification: This is a standard operational surface for content transformation skills and poses no elevated risk due to the absence of exploitable capabilities within the skill.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 17, 2026, 02:09 AM