v0.4.8 — prompt injection firewall, issue resolver profiles, bg_remover hardening

Added

• Skill — security/prompt_injection_firewall — offline deterministic pre-flight scanner (hidden text, Unicode/confusable evasion, nested encodings, instruction overrides, corroboration-based sensitivity, sanitization output) (#46, #267).
• dev_tools/issue_resolver — v0.3 repository profiles: ordered profile_urls, load_repository_profile parsing with provenance-labelled context, profile standard doc, Skillware dogfood profile at .github/ISSUE_RESOLVER.md (#145, #271).
• Documentation — docs/contributing/issue_resolver_profile.md — normative contract and examples for repository-maintained agent context files.

Changed

• creative/bg_remover — v0.2.0 hardening: rembg session reuse, Base64/file validation, 25 MB limit, path traversal rejection, parent mkdir for output_path, examples/bg_remover_demo.py, expanded bundle tests (#257, #268).
• dev_tools/issue_resolver — Profile discovery prefers .github/ISSUE_RESOLVER.md over repo-root fallback; expanded dogfood profile aligned with contributor workflow.
• Version policy — Security support floor raised to >= 0.4.7; legacy band 0.3.5–0.4.6 (upgrade recommended, silent CLI); unsupported advisory for installs below 0.3.5.

Upgrade

pip install -U skillware

Dev / multi-skill:

pip install -U "skillware[dev,all,agents]"

Per-skill extras:

pip install -U "skillware[security_prompt_injection_firewall]"
pip install -U "skillware[creative_bg_remover]"
pip install -U "skillware[dev_tools_issue_resolver]"

See CHANGELOG.md and Install extras.

Contributors

• @mrmasa88 — security/prompt_injection_firewall skill (#267)
• @AyushSrivastava1818 — creative/bg_remover v0.2.0 hardening (#268)
• @TheDarkniteFalls — issue resolver repository profiles (#271)
• @rosspeili — release cut, dogfood profile, version policy

Full changelog

• #267 — Add security/prompt_injection_firewall skill (#46)
• #268 — Harden creative/bg_remover to v0.2.0 (#257)
• #271 — Add repository profiles to issue resolver (#145)