The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill is designed to process data from untrusted external sources, creating a surface for potential indirect prompt injection attacks.
Ingestion points: The skill retrieves data and structural information from user-supplied Excel templates and SEC EDGAR filings as described in SKILL.md and references/sec-filings.md.
Boundary markers: The instructions do not specify the use of delimiters or guidelines for the agent to ignore instructions embedded within the ingested data.
Capability inventory: The skill has the ability to write to files and modify workbooks using Office JS and the openpyxl Python library.
Sanitization: There is no mention of sanitizing or validating the content extracted from external sources before it is used.
[COMMAND_EXECUTION]: The SKILL.md file contains an instruction to execute a script named recalc.py when generating standalone Excel files via Python. This script is not included in the skill's distribution, which could lead to the execution of an unverified or potentially malicious resource if provided at runtime.

3-statement-model