The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted data from the repository being scanned, which could contain malicious instructions hidden in markdown or configuration files designed to manipulate the generated report.
Ingestion points: The skill scans package.json, requirements.txt, Cargo.toml, go.mod, and README files in the repository as stated in the Behavior Checklist section of SKILL.md.
Boundary markers: The instructions do not define explicit delimiters or warnings to the agent to ignore instructions embedded within the scanned files.
Capability inventory: The skill's capabilities are limited to reading repository files and writing markdown documentation to the .lcs/work-items/ directory. It does not possess network access or arbitrary command execution capabilities.
Sanitization: There is no mention of sanitization, filtering, or validation of the content extracted from the external repository files before it is interpolated into the onboarding reports.

lcs-onboarding