The Agent Skills Directory

[COMMAND_EXECUTION]: The skill uses the Bash tool to execute find, grep, and xargs for scanning project directories. These commands identify analytics libraries in manifest files and tracking calls within source code. The execution is scoped to the local environment for auditing purposes.
[PROMPT_INJECTION]: The skill is subject to indirect prompt injection because it reads and analyzes content from untrusted files in the target project. * Ingestion points: Source files (.ts, .js, .py) and documentation (.md) are read during the tracking call and metric inventory steps. * Boundary markers: The instructions lack delimiters or explicit warnings to prevent the agent from following instructions embedded within the audited code. * Capability inventory: The skill can access Bash, Read, WebFetch, and WebSearch tools, which could be leveraged if malicious instructions are successfully injected. * Sanitization: No sanitization or verification of the file content is performed before it is processed by the agent.

lumen-recon