The Agent Skills Directory

[EXTERNAL_DOWNLOADS]: The skill is configured to prioritize fetching content from context7.com, a documentation aggregator. It also performs automated cloning of external GitHub repositories to the local environment.
[COMMAND_EXECUTION]: The skill uses shell commands to manage its environment and tools, including:
Installing the repomix utility via npm install -g repomix (file: SKILL.md).
Executing git clone to download full repository source code into the /tmp/docs-analysis directory (file: WORKFLOWS.md).
Running the repomix command to generate AI-friendly repository summaries.
Using pkill -9 repomix for process management in its error-handling routines (file: references/error-handling.md).
[INDIRECT_PROMPT_INJECTION]: As the skill's primary function is to ingest and summarize external documentation, it inherently possesses an attack surface for indirect prompt injection.
Ingestion points: The skill reads data from various documentation URLs via WebFetch and clones entire codebases via git (files: SKILL.md, WORKFLOWS.md).
Boundary markers: There are no explicit instructions to the agent to treat ingested data as untrusted or to use delimiters to prevent the agent from following instructions embedded in the documentation.
Capability inventory: The agent has the ability to execute network searches, fetch web pages, write files to /tmp, and execute shell commands.
Sanitization: The skill lacks explicit sanitization steps for the data retrieved from external repositories or documentation sites.

docs-seeker