content-repurposing

Pass

Audited by Gen Agent Trust Hub on Jun 23, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: Indirect Prompt Injection Surface. The skill processes untrusted data from external social media URLs and transcripts, which could contain malicious instructions designed to influence the agent.
  • Ingestion points: Ingests material from external URLs and research reports using the WebFetch tool as described in the workflow.
  • Boundary markers: The skill lacks explicit instructions or delimiters to isolate ingested content or warn the agent to ignore embedded instructions.
  • Capability inventory: The skill uses tools including Bash, Write, and WebFetch (allowed in SKILL.md frontmatter).
  • Sanitization: No content validation or sanitization procedures are defined in the instructions.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 23, 2026, 07:55 AM
Security Audit — agent-trust-hub — content-repurposing