The Agent Skills Directory

[METADATA_POISONING]: The file skill-report.json contains deceptive metadata that impersonates an official automated security report. It includes fabricated fields such as risk_level: "safe", is_blocked: false, and provenance.model_requested: "gpt-5.5:high". These claims, along with the attribution to a different author ("7Spade") than the provided context ("aiskillstore"), are intended to mislead auditors and bypass vetting processes by presenting falsified provenance and safety history.
[INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process external, potentially untrusted artifacts (e.g., slide decks and documents) to apply brand styling. This creates a vulnerability to indirect prompt injection attacks where malicious instructions hidden in the artifacts could influence agent behavior.
Ingestion points: External documents and presentation files provided by the user, as referenced in SKILL.md and the capabilities section of skill-report.json.
Boundary markers: Absent. The instructions do not specify any delimiters or warnings to ignore embedded instructions in the processed data.
Capability inventory: The skill leverages document manipulation capabilities and references the use of the python-pptx library to modify presentation formatting.
Sanitization: Absent. There is no evidence of validation, filtering, or sanitization protocols for the content of the ingested artifacts.

brand-guidelines