The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill is designed to process and analyze untrusted source code provided by the user, which could contain malicious prompt instructions designed to influence the agent's behavior.
Ingestion points: File paths and content provided through arguments or discovered via directory scanning in SKILL.md.
Boundary markers: The skill does not provide clear delimiters or instructions for the agent to treat the analyzed code strictly as data, increasing the risk of the agent obeying embedded commands.
Capability inventory: The skill instructs the agent to perform file system operations and execute shell commands (npm, eslint, semgrep).
Sanitization: No sanitization or validation of the input code is performed before it is processed by the agent.
[COMMAND_EXECUTION]: The instructions direct the agent to execute several shell commands, including npm install, eslint, and semgrep. While these are legitimate developer tools, command execution on external input is a significant capability that requires careful handling.

frontend-mobile-security-xss-scan