The Agent Skills Directory

[COMMAND_EXECUTION]: The skill instructs the agent to automatically execute a directory listing command (ls) upon first activation to scan for the presence of recommended companion skills in various local directory paths.
[EXTERNAL_DOWNLOADS]: The skill recommends the installation of external components from the AbsolutelySkilled registry via npx commands.
[PROMPT_INJECTION]: The skill exhibits an indirect prompt injection surface due to its core function of processing untrusted external data.
Ingestion points: The skill is designed to analyze support ticket titles, customer messages, and verbatim survey feedback as described in SKILL.md.
Boundary markers: The instructions lack explicit boundary markers or delimiters to separate the untrusted ticket data from the agent's instruction context.
Capability inventory: The skill leverages shell command execution capabilities for environment reconnaissance (ls) and package management (npx).
Sanitization: No sanitization, escaping, or validation measures are prescribed for the ingested support data.

support-analytics