The Agent Skills Directory

[COMMAND_EXECUTION]: The skill executes local Python scripts (scripts/dfs_client.py and scripts/report_publish.py) to perform search engine results page (SERP) analysis and generate branded reports. These scripts are referenced as part of the skill's operational flow but were not provided in the skill package for inspection.
[INDIRECT_PROMPT_INJECTION]: The skill fetches and processes content from external websites, which creates a potential surface for indirect prompt injection if the source content contains malicious instructions.
Ingestion points: The skill uses webfetch to retrieve content from user-provided URLs and top-ranking competitor pages identified during the SERP audit.
Boundary markers: There are no explicit delimiters or instructions to ignore potential commands embedded in the fetched web content.
Capability inventory: The skill has the ability to execute shell commands (via Python scripts) and write files to the local file system.
Sanitization: No sanitization or validation steps are defined for the data retrieved from external URLs before it is processed and used to generate outlines.
[DATA_EXFILTRATION]: The skill accesses the host environment variable SEO_REPORTS_DIR to determine the file path for saving generated reports and writes output files to the local disk. While consistent with the skill's stated purpose of SEO reporting, this pattern involves reading system configuration and persistent file writing.

heading-optimizer