The Agent Skills Directory

[EXTERNAL_DOWNLOADS]: The skill installs the treeherder-cli tool from a third-party GitHub repository (github.com/padenot/treeherder-cli) using the Rust cargo package manager and executes the lumberjackth package from PyPI via uvx.\n- [COMMAND_EXECUTION]: The skill executes external CLI tools (treeherder-cli, lj) on the host system to query CI data, using arguments such as revision hashes and job IDs derived from user input.\n- [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it ingests and processes untrusted data from CI logs and failure summaries fetched from remote servers.\n
Ingestion points: Job logs and error summaries retrieved from treeherder.mozilla.org.\n
Boundary markers: Absent. The skill does not use specific delimiters to isolate potentially malicious instructions within the fetched data.\n
Capability inventory: Execution of CLI tools, local file system access for artifact downloads, and network requests to external APIs.\n
Sanitization: Absent. There is no evidence of sanitization or filtering of the fetched content before it is processed by the agent.

treeherder