kafka-development-practices
Pass
Audited by Gen Agent Trust Hub on Mar 3, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The
SKILL.mdfile includes a 'Memory Protocol' section that explicitly instructs the agent to execute the shell commandcat .claude/context/memory/learnings.mdat the start of an interaction to retrieve previous context. - [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it processes external source code and memory files while possessing broad capabilities.
- Ingestion points: The agent is configured to operate on
**/*.scalafiles and reads the.claude/context/memory/learnings.mdfile. - Boundary markers: There are no explicit instructions or delimiters defined to prevent the agent from following instructions embedded within the analyzed Scala code or the memory file.
- Capability inventory: The skill is granted access to the
Read,Write,Edit, andBashtools, allowing for arbitrary subprocess execution and filesystem modifications. - Sanitization: No sanitization or validation logic is present to filter malicious instructions from the ingested files before processing them.
Audit Metadata