tsconfig-json-rules
Pass
Audited by Gen Agent Trust Hub on Mar 3, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The
SKILL.mdfile contains a 'Memory Protocol' section that instructs the agent to execute a shell command (cat .claude/context/memory/learnings.md) to retrieve stored context before starting tasks. - [PROMPT_INJECTION]: The skill is subject to potential indirect prompt injection as it is designed to ingest and process external
tsconfig.jsonfiles and read from a local memory file. - Ingestion points: Processes
tsconfig.jsonfiles based on glob patterns and reads.claude/context/memory/learnings.mdvia shell command. - Boundary markers: No specific delimiters or warnings to ignore embedded instructions are present in the provided files.
- Capability inventory: The skill is granted
Read,Write, andEdittools, and the instructions mandate the use of shell commands for file reading. - Sanitization: No sanitization or validation logic is implemented for the content of the files being processed.
Audit Metadata