offensive-social-engineering
Pass
Audited by Gen Agent Trust Hub on Nov 3, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTIONNO_CODE
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill instructions define a workflow for analyzing external artifacts such as source code, binary files, and runtime configurations. This creates a surface where malicious instructions embedded in those artifacts could potentially manipulate the agent's behavior during an audit.
- Ingestion points: Source code, binaries, and runtime configurations (specified in the operational workflow of
SKILL.md). - Boundary markers: The instructions do not specify the use of delimiters or specific guidelines to ignore instructions found within processed artifacts.
- Capability inventory: The skill references capabilities for file searching (
rg), AST analysis, decompilation, and executing test suites (npm test). - Sanitization: No explicit sanitization or validation steps for external content are defined.
- [COMMAND_EXECUTION]: The audit workflow directs the agent to execute shell commands, including
rg(ripgrep) for searching andnpm testfor verifying remediation code. - [NO_CODE]: The skill consists entirely of markdown instructions and YAML metadata; it does not include any scripts, compiled binaries, or defined third-party software dependencies.
Audit Metadata