codecontext-setup

Pass

Audited by Gen Agent Trust Hub on Mar 28, 2026

Risk Level: SAFEPROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
  • [PROMPT_INJECTION]: The skill facilitates an indirect prompt injection surface by instructing agents to process '@context' annotations within repository files. This data enters the agent context and can influence its reasoning or actions.
  • Ingestion points: Repository source code and documentation files via '@context' markers.
  • Boundary markers: No explicit delimiters or 'ignore' instructions are provided for the annotation content to prevent embedded command overrides.
  • Capability inventory: The agent has the ability to execute shell commands via npx and modify repository files.
  • Sanitization: The skill does not prescribe sanitization or validation for the annotations.
  • [COMMAND_EXECUTION]: The skill directs the agent to run CLI tools such as '@recallnet/codecontext-cli' using npx. These commands are consistent with the installation and use of the author's own software for repository analysis and reporting.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 28, 2026, 04:59 PM