instantly-debug-bundle
Pass
Audited by Gen Agent Trust Hub on Sep 11, 2026
Risk Level: SAFEDATA_EXFILTRATIONINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill exhibits an indirect prompt injection surface by ingesting data from external API endpoints.
- Ingestion points: Instantly.ai API endpoints for campaigns, accounts, and error messages (referenced in SKILL.md).
- Boundary markers: None; data is written directly to a JSON file via
fs.writeFileSync. - Capability inventory:
Bash(curl)for network requests,Writefor local file storage, andEditfor file modification. - Sanitization: No specific sanitization or filtering is applied to the content retrieved from the API before it is saved.
- [DATA_EXFILTRATION]: The skill is designed to aggregate and export sensitive organizational data, including email addresses, campaign metrics, lead statistics, and webhook configurations from a SaaS provider (Instantly.ai) to a local file. While this is the intended primary purpose of a 'debug bundle' tool, it constitutes significant data exposure.
- [COMMAND_EXECUTION]: The skill provides automated Bash scripts that use
curlto interact with the Instantly.ai API v2, utilizing theINSTANTLY_API_KEYenvironment variable for authentication.
Audit Metadata