skyrim-base-object-swapper
Pass
Audited by Gen Agent Trust Hub on Oct 15, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted
*_SWAP.iniconfiguration files which could contain malicious instructions intended to influence the agent's behavior. - Ingestion points: The
scripts/audit_bos_configs.pyscript reads the contents of all*_SWAP.inifiles found recursively within a user-provided directory. - Boundary markers: There are no boundary markers or instructions to the agent to ignore potentially malicious content embedded within the data of the configuration files.
- Capability inventory: The skill possesses the capability to execute shell commands (running the Python audit and linter scripts).
- Sanitization: While the script performs regex validation for specific syntax errors, it does not sanitize the input against prompt injection patterns that might be hidden in comments or values.
- [COMMAND_EXECUTION]: The skill instructions direct the agent to execute Python scripts on the local system.
- Evidence:
SKILL.mdprovides commands for the agent to run:python ..\skyrim-distr-kid-validation\scripts\lint_framework_configs.py <directory>andpython scripts\audit_bos_configs.py <directory>.
Audit Metadata