ripdpi-app-network-architect
Pass
Audited by Gen Agent Trust Hub on Sep 5, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes external repository code which is untrusted data.\n
- Ingestion points: The skill analyzes source files in a provided directory path using the analyze_app_network_surface.py script and direct file access as described in SKILL.md.\n
- Boundary markers: The skill instructions advise verifying all scanner findings against source code and tests, providing a manual review step, though no explicit data delimiters are used in the prompt instructions.\n
- Capability inventory: The skill performs file system reads, writes (upon user request), and local execution of its provided Python analysis script.\n
- Sanitization: The analyze_app_network_surface.py script performs static regex-based scanning and does not execute or evaluate any code it reads from target files.\n- [COMMAND_EXECUTION]: The skill instructions direct the agent to execute a local Python script for repository analysis.\n
- Evidence: SKILL.md contains a bash command
python3 .agents/skills/ripdpi-app-network-architect/scripts/analyze_app_network_surface.py . --max-findings 80.\n - Context: The script is part of the skill's own package and performs static analysis without network access or dynamic code evaluation.
Audit Metadata