The Agent Skills Directory

[COMMAND_EXECUTION]: The skill provides detailed instructions for the agent to execute the octocode CLI binary to perform various file system and network operations.
[EXTERNAL_DOWNLOADS]: The skill allows the agent to fetch repository structures, read remote files, and clone repositories from GitHub and npm using the CLI tool.
[PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection (Category 8) because it ingests untrusted data from external sources.
Ingestion points: The agent reads code, PR descriptions, and package info from external GitHub and npm repositories via octocode cat, octocode grep, octocode pr, and octocode clone commands.
Boundary markers: No explicit boundary markers or instructions to ignore embedded commands in the processed data are provided in the skill instructions.
Capability inventory: The agent has the capability to execute shell commands (octocode) and read/write to the local filesystem.
Sanitization: There is no mention of sanitizing or escaping the content retrieved from external sources before it is processed by the agent.
[CREDENTIALS_UNSAFE]: The skill documentation references the use of sensitive environment variables such as GITHUB_TOKEN, OCTOCODE_TOKEN, and GH_TOKEN for authentication. While this is standard practice for CLI tools interacting with the GitHub API, it highlights the agent's access to sensitive credentials.

octocode