pentesting-checklist-usage
Pass
Audited by Gen Agent Trust Hub on Sep 18, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill provides setup instructions involving cloning a repository from GitHub (
github.com/m14r41/PentestingChecklist) and installing dependencies vianpmorpnpm. These are standard developmental instructions referencing a well-known service. - [INDIRECT_PROMPT_INJECTION]: The application described in the skill supports importing JSON files to restore previous assessment states, which represents a potential attack surface for indirect prompt injection if an attacker provides a malicious JSON file to the user or agent.
- Ingestion points: Import functionality for assessment data in JSON format (described in SKILL.md).
- Boundary markers: None mentioned in the skill documentation.
- Capability inventory: The skill is purely informational and does not grant the agent automated capabilities like subprocess execution or direct file writes.
- Sanitization: No data validation or sanitization processes are described for the imported JSON content.
Audit Metadata