instagram-account-research
Pass
Audited by Gen Agent Trust Hub on May 8, 2026
Risk Level: SAFENO_CODE
Full Analysis
- [NO_CODE]: The skill file consists entirely of markdown instructions and YAML metadata without any embedded scripts, shell commands, or executable code blocks.
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process external data from Instagram profiles and posts, which is a common surface for indirect prompt injection if that content contains malicious instructions.
- Ingestion points: External data flows into the agent through the
instagram-profilesandinstagram-postscollection keys inSKILL.md. - Boundary markers: The instructions do not explicitly define delimiters or specific 'ignore' instructions for the external content.
- Capability inventory: The skill definition does not provide the agent with local file-system write access (outside its own work folder), network exfiltration tools, or command execution capabilities.
- Sanitization: No explicit sanitization or filtering of the Instagram data is mentioned in the workflow.
Audit Metadata