function-length-and-responsibility
Pass
Audited by Gen Agent Trust Hub on Mar 3, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The SKILL.md file includes a 'Memory Protocol' section that instructs the agent to execute a bash command (
cat .claude/context/memory/learnings.md) to retrieve previous context. While used for continuity, executing shell commands to read internal files is a security risk. - [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it is designed to ingest and process untrusted code from a 'target' path defined in its schema.
- Ingestion points: The 'target' file or path provided via the input schema (schemas/input.schema.json).
- Boundary markers: There are no explicit instructions to ignore embedded commands or markers to delimit external content.
- Capability inventory: The skill has access to file system tools (Read, Write, Edit) and shell command execution (cat).
- Sanitization: No sanitization or validation of the input file content is performed before processing.
Audit Metadata