pentest-reporting
Pass
Audited by Gen Agent Trust Hub on Sep 19, 2026
Risk Level: SAFEDYNAMIC_EXECUTIONINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTIONEXTERNAL_DOWNLOADS
Full Analysis
- [DYNAMIC_EXECUTION]: The skill contains multiple Bash and Python script templates in
payloads.mdandguides/password-audit-reporting.mdintended to be generated and executed by the agent. These scripts automate reporting tasks such as finding correlation, deduplication, and statistical analysis of password audits. - [INDIRECT_PROMPT_INJECTION]: The skill's primary workflow involves ingesting and parsing data from external security tools (e.g., Nmap, Burp Suite, Nessus). This creates an attack surface where maliciously crafted tool outputs could attempt to influence the agent's behavior.
- Ingestion points: Processes XML scan reports (Nmap, Burp, Nessus) and cracked password lists as described in
guides/dradis-faraday-reporting.mdandguides/password-audit-reporting.md. - Boundary markers: The processing scripts do not implement explicit boundary markers or directives to ignore instructions embedded within the ingested data.
- Capability inventory: The skill utilizes
Bash,Write, andAgenttools to process the ingested data. - Sanitization: While sanitization techniques (e.g., using
sedorexiftool) are documented as best practices inpayloads.md, they are not automatically enforced by the core processing logic. - [COMMAND_EXECUTION]: The skill executes various local system commands and services, including
dradis,faraday-server,cutycapt, andrecordmydesktop. The documentation inguides/dradis-faraday-reporting.mdsuggests binding the Dradis server to all network interfaces (-b 0.0.0.0) for team collaboration, which may increase the network attack surface of the host. - [EXTERNAL_DOWNLOADS]: The skill includes instructions in
payloads.mdto download the Serpico reporting project from its official GitHub repository. GitHub is a well-known service, and this download is a documented part of the skill's reporting functionality.
Audit Metadata