go-expert
Pass
Audited by Gen Agent Trust Hub on Mar 3, 2026
Risk Level: SAFEPROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [PROMPT_INJECTION]: The skill exhibits a vulnerability surface for indirect prompt injection. Ingestion points: The skill operates on user-specified files or paths via the 'target' parameter in 'schemas/input.schema.json'. Boundary markers: The prompt instructions in 'SKILL.md' do not include explicit delimiters or instructions to ignore commands within processed files. Capability inventory: The skill has access to powerful tools including 'Bash', 'Write', 'Edit', and 'Grep'. Sanitization: No sanitization or content validation is implemented for the data ingested from target files.
- [COMMAND_EXECUTION]: The skill instructions define a mandatory protocol involving the execution of a system command. Evidence: 'SKILL.md' requires the agent to run 'cat .claude/context/memory/learnings.md' to manage persistent memory state.
Audit Metadata