The Agent Skills Directory

[COMMAND_EXECUTION]: The skill instructs the agent to use the Bash tool for executing various shell commands including grep, jq, ls, wc, and npx tsx. These commands are used to analyze local extraction logs, check file system state, and run local project CLI tools for site inspection.
[EXTERNAL_DOWNLOADS]: The skill uses curl to fetch headers and content from remote URLs associated with the site being debugged. This is part of the 'Probe' phase to identify site-specific issues like rate limiting or bot detection.
[PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it processes untrusted data while possessing significant system capabilities.
Ingestion points: Untrusted data enters the agent context via extraction-log.jsonl, output.wxr, and HTML content fetched from external source URLs using curl probes.
Boundary markers: Absent. The instructions do not specify using delimiters or "ignore instructions" warnings to separate untrusted data from the agent's core instructions.
Capability inventory: Across its scripts and instructions, the skill allows for arbitrary command execution via Bash, file modification via Edit and Write, and network access via WebSearch and curl commands.
Sanitization: Absent. There is no mention of filtering, escaping, or validating the external content before it is processed by the agent.

diagnose