The Agent Skills Directory

[SAFE]: The skill consists of legitimate technical documentation for the ESP32 platform. All commands and tools referenced (e.g., idf.py, openocd, gdb) are standard industry tools for embedded development. No unauthorized external network connections or data exfiltration patterns were detected.
[SAFE]: The provided example script ge-coredump-parse.sh is designed for local analysis of crash logs. It implements shell safety best practices (e.g., set -euo pipefail) and performs validation on file paths before execution.
[SAFE]: The skill includes a dedicated privacy section advising users to de-identify sensitive data like network credentials from diagnostic logs before sharing them, which aligns with security best practices.
[INDIRECT_PROMPT_INJECTION]: The skill contains a vulnerability surface for indirect prompt injection via the processing of coredump files.
Ingestion points: The ge-coredump-parse.sh script accepts a coredump file as input for analysis.
Boundary markers: Absent. The output from the idf.py tool is displayed to the agent without specific delimiters or warnings regarding embedded instructions.
Capability inventory: The skill facilitates file reading and the execution of the idf.py debugging toolchain.
Sanitization: The skill does not sanitize the content of the coredump files, relying instead on the idf.py parser. This represents a standard, low-risk functional surface for a debugging utility.

esp32-debug