The Agent Skills Directory

[SAFE]: The skill is focused on structured risk analysis (FMEA, Fault Tree Analysis, Swiss Cheese model) and explicitly states it does not write or modify code.\n- [SAFE]: No evidence of prompt injection, data exfiltration, or persistence mechanisms was found. The instructions reinforce safety by requiring quantitative scores and prohibiting the conclusion of 'no risk'.\n- [SAFE]: The skill handles project-related data (specifications and designs) but lacks the operational capabilities (such as shell execution or network access) that would make it a significant vector for indirect prompt injection attacks.\n- [SAFE]: All referenced files contain standard documentation, templates, and methodologies for failure analysis with no malicious or obfuscated content.

omen