local-methylation-profile
Pass
Audited by Gen Agent Trust Hub on Apr 15, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill instructs the agent to construct and execute an
awkcommand using user-provided column indices (<i_methylation>,<i_coverage>). This dynamic command construction is a potential injection vector if the agent does not strictly validate that the inputs are numeric or safe column identifiers. - [PROMPT_INJECTION]: The skill processes untrusted external genomic data (
methylation.bed,target_regions.bed), which represents an indirect prompt injection surface. - Ingestion points: Data enters the context via
methylation.bedandtarget_regions.bedfiles used in Step 1 and Step 2. - Boundary markers: There are no explicit delimiters or instructions provided to the agent to distinguish data content from potential instructions.
- Capability inventory: The skill allows for shell command execution (
awk) and uses specialized bioinformatics tools (mcp__methyl-tools). - Sanitization: No validation or sanitization steps are defined for the content of the processed genomic files.
Audit Metadata