The Agent Skills Directory

[PROMPT_INJECTION]: The skill exhibits an indirect prompt injection surface where untrusted user data is interpolated into command structures.
Ingestion points: Lead information including first names, last names, company domains, and LinkedIn profiles are ingested and processed in SKILL.md (Steps 1, 3, 4, and 5).
Boundary markers: Absent. The skill does not use delimiters or explicit instructions to the agent to ignore potentially malicious content within the lead data.
Capability inventory: The agent utilizes the orth run command to execute external tools and has read access to the local MEMORY.md file.
Sanitization: There is no evidence of input validation, escaping, or filtering of the lead data before it is used in shell arguments or JSON payloads.
[COMMAND_EXECUTION]: The skill executes external enrichment tools (Hunter, Sixtyfour, Fiber) using the orth run platform command. These operations are consistent with the skill's stated purpose of lead enrichment and target well-known B2B data services.
[COMMAND_EXECUTION]: The skill instructs the agent to read MEMORY.md to establish project context, such as the Ideal Customer Profile (ICP), prior to performing enrichment tasks.

lead-enrichment