The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill presents a vulnerability surface for indirect prompt injection where malicious instructions could be ingested from the workspace.
Ingestion points: The skill is configured to use Read, Glob, and Grep tools to read content from the local environment (SKILL.md).
Boundary markers: The skill does not provide any delimiters, boundary markers, or specific instructions to ignore embedded commands when processing external file content.
Capability inventory: The skill has access to high-privilege tools including Bash for shell execution and Write/Edit for file system modifications.
Sanitization: No sanitization, validation, or escaping logic is defined for data read from the environment before it is passed to execution tools.
[METADATA_POISONING]: The skill content is misleading and inconsistent with its stated technical purpose.
Although the skill is titled 'pytest-advanced' and describes Python testing concepts, the code examples provided are written in JavaScript syntax while being explicitly labeled as Python in the markdown blocks.
The documentation is largely composed of generic placeholders and high-level boilerplate descriptions (e.g., 'Feature 1', 'Common Issue 1') rather than functional Pytest configurations, which could lead to agent confusion or incorrect tool usage.

pytest-advanced