The Agent Skills Directory

[SAFE]: The skill provides a structured and transparent process for researching competitors using public data. It implements best practices such as persisting raw data for auditing and referencing sources.
[PROMPT_INJECTION]: The skill is vulnerable to indirect prompt injection because it ingests and synthesizes content from untrusted external websites provided by the user.
Ingestion points: External web content is ingested into the agent context via the firecrawl_scrape tool as documented in SKILL.md and references/tool-reference.md.
Boundary markers: The instructions in SKILL.md do not define boundary markers (such as XML tags or specific delimiters) or provide "ignore embedded instructions" warnings when the agent processes the scraped markdown content.
Capability inventory: The agent has the capability to write files to the competitor-profiles/ directory in the project root, as described in the "Saving Raw Data" and "Output Format" sections of SKILL.md.
Sanitization: No sanitization, escaping, or validation of the retrieved web content is performed before the agent uses it to synthesize the final profile.

competitor-profiling