The Agent Skills Directory

[PROMPT_INJECTION]: The skill possesses an indirect prompt injection surface as it ingests untrusted data from external websites and community forums.
Ingestion points: Public salary platforms and anonymous community sources processed during Step 3 (Research) in SKILL.md.
Boundary markers: Absent. The procedure does not specify delimiters or instructions to ignore embedded commands within the fetched data.
Capability inventory: File system access via Read and Write tools, and restricted shell capabilities via Bash (mkdir, test, date) as defined in the frontmatter and Procedure section of SKILL.md.
Sanitization: Absent. No explicit sanitization or validation of the fetched external content is mentioned before it is processed or stored in the cache.

salary-research