The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill ingests and processes untrusted data from external websites, creating a surface for potential indirect prompt injection attacks.\n
Ingestion points: The skill uses curl to fetch rendered HTML from live URLs as part of the workflow in SKILL.md and references/seo-checklist.md.\n
Boundary markers: There are no explicit instructions to use delimiters or ignore instructions embedded within the fetched HTML content.\n
Capability inventory: The skill uses curl for network access and writes detailed audit reports to the local file system (docs/reports/).\n
Sanitization: No sanitization or validation of the external HTML content is described before the agent processes it for analysis.\n- [COMMAND_EXECUTION]: The skill instructs the agent to execute shell commands, specifically curl -s <url>, to retrieve content from external servers. This involves network interaction with untrusted remote hosts.

findable