The Agent Skills Directory

[PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection due to its core functionality.
Ingestion points: The skill reads and processes external codebase files using the Read and Grep tools as specified in SKILL.md.
Boundary markers: Absent. There are no instructions or delimiters defined to prevent the agent from following malicious instructions found within the code being analyzed.
Capability inventory: The skill is granted access to the Bash tool, which provides significant system interaction capabilities.
Sanitization: Absent. The instructions do not prescribe any validation or escaping of the content retrieved from searched files.
[COMMAND_EXECUTION]: The skill's workflow involves the execution of various shell commands (e.g., grep, git blame, git log) via the Bash tool. While these are necessary for the skill's purpose, they represent a high capability tier that increases the impact of potential prompt injections.

codebase-search