ig-repurpose
Pass
Audited by Gen Agent Trust Hub on Sep 14, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill's primary function is to act as a content creation assistant. It follows a structured logic for extracting claims, numbers, stories, and mechanisms from user-provided assets to generate social media drafts. No signs of obfuscation, privilege escalation, or malicious persistence were found.
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to process untrusted external data, such as transcripts, articles, and content from URLs. This creates a theoretical surface for indirect prompt injection if the ingested data contains instructions for the AI.
- Ingestion points: The skill accepts transcripts, articles, newsletters, scripts, call summaries, livestreams, and URL content as input in
SKILL.md. - Boundary markers: The instructions do not define specific delimiters or "ignore instructions" tags for the ingested content.
- Capability inventory: The skill's capabilities are limited to text processing and drafting via internal tool calls (
/ig-reel,/ig-human). It lacks high-risk capabilities like shell execution, network exfiltration, or sensitive file system access. - Sanitization: There is no explicit sanitization logic mentioned for the external content before it is processed.
Audit Metadata