The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data from multiple external sources, creating a potential vector for indirect prompt injection.
Ingestion points: SKILL.md specifies reading "market notes", "pasted Perplexity output", and "competitor URLs" to build the analysis.
Boundary markers: There are no instructions to use delimiters or to treat ingested external content as untrusted data.
Capability inventory: The skill utilizes Read and Write tools to analyze workspace files and generate a competitive analysis report.
Sanitization: The methodology does not include steps to sanitize or filter the content of external reports or URLs before they are processed by the agent.

analyze-competition