The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill ingests external code for analysis, creating a potential surface for indirect prompt injection.\n
Ingestion points: The skill uses the Read tool to ingest code from file or module paths specified in $ARGUMENTS.\n
Boundary markers: There are no explicit instructions or delimiters defined to prevent the agent from following instructions embedded within the code being analyzed.\n
Capability inventory: The skill is restricted to the Read and Grep tools, significantly limiting the risk as the agent cannot exfiltrate data or modify the system.\n
Sanitization: The skill does not perform sanitization or filtering on the ingested code content.

deep-modules