The Agent Skills Directory

[COMMAND_EXECUTION]: The skill uses standard shell commands (find, grep, xargs) to identify power management implementation details (e.g., esp_deep_sleep_start(), pm_state_force) within the local project directory. These commands are consistent with the skill's stated purpose of auditing code.
[EXTERNAL_DOWNLOADS]: The skill is configured to use standard web-retrieval tools (WebFetch, WebSearch) to look up platform-specific documentation. No unauthorized remote script execution or binary downloads were found.
[DATA_EXFILTRATION]: No patterns were detected that involve reading sensitive system files (e.g., .ssh, .aws) or transmitting credentials to external servers. The skill focuses on analyzing technical source code related to battery and power management.
[PROMPT_INJECTION]: The instructions do not contain any directives intended to bypass safety guardrails, override system prompts, or extract internal instructions.
[INDIRECT_PROMPT_INJECTION]: The skill has a surface for indirect prompt injection as it ingests untrusted source code from the user's project.
Ingestion points: Project source files (.c, .cpp, .h, .rs) and build configuration files (sdkconfig, prj.conf).
Boundary markers: Absent; the skill does not wrap the found code in delimiters or warn the agent about potential embedded instructions.
Capability inventory: Bash, Write, Edit, WebFetch, WebSearch tools are available.
Sanitization: No specific sanitization or filtering of the read content is performed before processing.

volt-power