drill-status
Pass
Audited by Gen Agent Trust Hub on Sep 24, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill executes
date +%Y-%m-%dvia the Bash tool to calculate the current date for its progress report. This is a benign use of command execution for time-tracking purposes. - [INDIRECT_PROMPT_INJECTION]: The skill ingests data from local files, which creates a surface for indirect prompt injection if those files contain malicious instructions.
- Ingestion points: The skill reads
~/.drill-me/index.mdand files within the~/.drill-me/topics/directory using theReadandGlobtools. - Boundary markers: Absent; the skill does not specify delimiters or instructions to the agent to disregard potential instructions within the read files.
- Capability inventory: The skill is restricted to
Read,Glob, andBashas specified in the frontmatter, limiting its ability to perform high-risk operations. - Sanitization: Absent; content from the data files is processed directly to identify weak spots and recommendations.
Audit Metadata