The Agent Skills Directory

[PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection attacks because it is designed to ingest and analyze untrusted code from external repositories.
Ingestion points: The skill uses Read, Grep, and Glob tools to ingest content from the target codebase for analysis (SKILL.md).
Boundary markers: No instructions are provided to implement delimiters or distinct markers to separate the skill's operational logic from the external data being processed.
Capability inventory: The skill utilizes read-only file system tools (Read, Grep, Glob) to identify patterns and conduct audits (SKILL.md).
Sanitization: The skill lacks sanitization or validation logic to prevent malicious instructions embedded in the audited code from influencing the agent's behavior.
[NO_CODE]: The skill is composed entirely of Markdown reference files and configuration data; it contains no executable scripts, binaries, or source code files.

sharp-edges