The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it is designed to ingest and analyze untrusted external data (codebases).
Ingestion points: The skill instructions in SKILL.md direct the agent to explore repositories using Glob and Grep and to read content from various files (e.g., package.json, README.md).
Boundary markers: The instructions lack explicit boundary markers or directives for the agent to ignore instructions that might be embedded within the files being analyzed.
Capability inventory: The skill facilitates file system discovery and read operations via the agent's available tools. No write or network capabilities are explicitly invoked by the skill itself.
Sanitization: There is no mention of sanitization, filtering, or validation of the content read from the repository files before it is processed by the agent's logic.

resume-project-analyzer