genpark-automated-email-marketing-agent
Pass
Audited by Gen Agent Trust Hub on Oct 8, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill requires cloning a repository from 'github.com/alphaparkinc/genpark-automated-email-marketing-agent-skill.git' and installing dependencies via pip.
- [COMMAND_EXECUTION]: The installation section provides shell commands for cloning the source code and installing Python packages.
- [INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted data from external sources such as CSV files ('data/contacts.csv') and recipient profiles. This data is interpolated into prompts for generating personalized email content, creating a vulnerability surface for indirect prompt injection.
- Ingestion points: 'segmenter.load_from_csv("data/contacts.csv")' and 'RecipientProfile' fields in 'SKILL.md'.
- Boundary markers: None observed in the documentation or implementation snippets to delimit user-provided data from instructions.
- Capability inventory: The skill has the ability to send emails via the SendGrid API ('CampaignExecutor'), write to a local SQLite database ('DatabaseManager'), and perform network operations for LLM content generation.
- Sanitization: No explicit evidence of sanitization or filtering of contact-provided fields before prompt interpolation was found.
Audit Metadata