aeon-skill-security-scan
Pass
Audited by Gen Agent Trust Hub on Sep 24, 2026
Risk Level: SAFE
Full Analysis
- [PROMPT_INJECTION]: The skill contains the phrase 'Ignore previous instructions' within a table describing threat patterns it is designed to detect in other skills. This is a descriptive reference for auditing purposes and does not constitute an attempt to override the agent's instructions.
- [INDIRECT_PROMPT_INJECTION]: The skill's primary function is to process untrusted data from other skill files (SKILL.md, scripts, and references). While this creates an ingestion surface for indirect prompt injection, the skill includes mitigation logic such as a 'code-fence downgrade' to prevent the agent from accidentally following instructions discovered during the scanning process.
- [EXTERNAL_DOWNLOADS]: The skill references resources from the vendor's repository on GitHub (BankrBot/skills) and the developer's repository (aaronjmars/aeon). These are legitimate functional references for the skill's distribution and documentation.
Audit Metadata