The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill's primary function involves reading and analyzing external documentation and API contract files, which could serve as a vector for indirect prompt injection if those files contain adversarial instructions.
Ingestion points: The agent reads .md, .bru, .json, and .ts (for schema) files during the Triage and Scan phases as specified in SKILL.md and references/scan-core.md.
Boundary markers: The instructions do not specify the use of delimiters or specific system instructions to treat the audited file content as untrusted data.
Capability inventory: The agent has access to shell commands (find, grep, sort) and the ability to modify documentation and contract files.
Sanitization: There is no evidence of sanitization or filtering of the file content before it is processed by the model.
[COMMAND_EXECUTION]: The skill relies on executing shell commands to perform file discovery and content analysis.
Evidence: The skill instructions in SKILL.md and reference materials in references/scan-core.md explicitly direct the agent to use find, grep, and sort to generate lists of artifacts and search for specific patterns within the codebase.

tend-docs