The Agent Skills Directory

[COMMAND_EXECUTION]: The skill executes discovery commands using grep and ls to scan project files like requirements.txt and pyproject.toml. These commands are used to detect used frameworks (e.g., Django, Flask) and libraries (e.g., OpenAI, LangChain) to tailor the Sentry configuration recommendations.
[EXTERNAL_DOWNLOADS]: The skill recommends installing the sentry-sdk package and framework-specific extras via pip. These packages are official resources from the vendor (getsentry) and are necessary for the skill's primary function.
[PROMPT_INJECTION]: The skill possesses an indirect prompt injection surface as it ingests untrusted data from project configuration files. Ingestion points: requirements.txt, pyproject.toml, setup.cfg, setup.py. Boundary markers: None explicitly used during file analysis. Capability inventory: Execution of discovery commands (grep, ls), recommendation of package installations (pip install), and generation of initialization code. Sanitization: The skill relies on specific regex pattern matching to identify dependencies, which limits the likelihood of accidental execution of instructions embedded in the analyzed files.

sentry-python-sdk