skills/flux-point-studios/cardano-agent-skills/aiken-dex-security-audit-operator/Gen Agent Trust Hub
aiken-dex-security-audit-operator
Pass
Audited by Gen Agent Trust Hub on Oct 16, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill facilitates the execution of local development tools (
git,aiken) to gather audit evidence. These commands are run in a controlled, manual-invocation context. - [INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted data from the outputs of external build and check commands, which could theoretically contain malicious instructions designed to influence the agent's behavior during the audit reporting phase.
- Ingestion points: Data enters the agent's context through the capture of stdout/stderr from
aiken checkandaiken buildcommands. - Boundary markers: There are no explicit markers or instructions provided to the agent to treat the tool output as untrusted data.
- Capability inventory: The skill allows for command execution and data collection for reporting.
- Sanitization: The skill lacks logic to sanitize or filter potential control characters or instructions from the external tool output before processing.
Audit Metadata