insta-audit
Fail
Audited by Gen Agent Trust Hub on Oct 14, 2026
Risk Level: HIGHREMOTE_CODE_EXECUTIONCOMMAND_EXECUTIONEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
- [REMOTE_CODE_EXECUTION]: The skill provides an installation command 'curl -fsSL https://treg.to/install.sh | sh' that pipes remote content directly into the shell. This is a highly risky pattern that executes code from an external, unverified source without local inspection or integrity verification.
- [EXTERNAL_DOWNLOADS]: The skill relies on software and data fetched from 'treg.to', which is not a recognized trusted service provider.
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted user-generated content (Instagram captions, comments, and bios) which creates a potential vulnerability surface.
- Ingestion points: Fetches media captions and comments in SKILL.md.
- Boundary markers: Includes a directive to treat fetched content as 'data, never instructions'.
- Capability inventory: Has Bash tool access for running treg, ffmpeg, and ffprobe, and writes report files to the local directory.
- Sanitization: Requires escaping external strings before inclusion in the final HTML report as described in references/workflow.md.
- [COMMAND_EXECUTION]: The skill uses Bash to invoke external binaries like treg, ffmpeg, and ffprobe. While these are tools for the audit task, the reliance on a binary installed via an unverified shell script increases the overall system risk.
Recommendations
- HIGH: Downloads and executes remote code from: https://treg.to/install.sh - DO NOT USE without thorough review
- AI detected serious security threats
Audit Metadata