The Agent Skills Directory

[COMMAND_EXECUTION]: The skill executes an external tool npx @ericrisco/rsc copy check to validate copywriting against banned phrases and runs a local shell script scripts/verify.sh for CSV validation. \n- [EXTERNAL_DOWNLOADS]: The use of npx results in the download and execution of the @ericrisco/rsc package from the npm registry at runtime. \n- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted content from the 02-DOCS/ directory, including brand studies and raw interview exports, to generate editorial plans. This creates a surface where embedded instructions in these documents could potentially influence the agent's planning output. \n
Ingestion points: 02-DOCS/ (brand study, pillars, raw inputs). \n
Boundary markers: Not present. \n
Capability inventory: Local script execution, external package execution via npx, and file system writes to 02-DOCS/. \n
Sanitization: No explicit sanitization or validation of the input file content before processing.

content-engine