The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill instructions direct the agent to ingest and analyze external, untrusted data to generate content strategies.
Ingestion points: SKILL.md identifies 'Keyword Data' (exports from Ahrefs/SEMrush), 'Call Transcripts' (sales/customer conversations), and 'Survey Responses' as primary sources for research.
Boundary markers: The instructions do not specify the use of delimiters or 'ignore embedded instructions' warnings when processing these external data sources.
Capability inventory: The skill is primarily analytical and uses web search tools for forum and competitor research, but it lacks high-risk capabilities such as arbitrary code execution, persistence mechanisms, or unauthorized file system writes.
Sanitization: No sanitization, validation, or filtering steps are defined for the ingested external content.

content-strategy